Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13937
    Prev
    Next
    INDEX
    Explanations

    technical or scientific terms and concepts, particularly in biology and chemistry.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @myinzi123

    programming commands and statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    programming and math-related terms, syntax, and function names, especially those related to code structure, mathematical notation, and technical keywords.

    oai_token-act-pair · gpt-4.1-2025-04-14Triggered by @ywhp2c8tjm

    code snippets related to software development or scientific publications related to medicine or biology.

    oai_token-act-pair · gemini-2.0-flashTriggered by @ywhp2c8tjm

    Code or mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical terms and expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ་་
    -0.66
    niſſe
    -0.51
    휀
    -0.49
     ſeine
    -0.47
    󠁢
    -0.47
    ſelben
    -0.46
     $_(
    -0.46
    SequentialGroup
    -0.46
     ſind
    -0.45
    存于互联网档案馆
    -0.45
    POSITIVE LOGITS
     AssemblyTitle
    0.61
    RegressionTest
    0.61
     tartalomajánló
    0.55
    principalTable
    0.52
     ویکی‌پدی
    0.48
    parsedMessage
    0.46
    KURZBESCHREIBUNG
    0.44
    GEBURTSDATUM
    0.42
    ⓧ
    0.41
     pungkasnya
    0.40
    Activations Density 11.811%

    No Known Activations