© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 14599
    Prev
    Next
    INDEX
    Explanations

    numerical values and related data structures

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

    Numbers within code or data structures

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isholm
    -0.47
    illett
    -0.47
    iddhar
    -0.44
     sub
    -0.44
     Jal
    -0.43
     Jaffe
    -0.43
    <bos>
    -0.43
     Raj
    -0.42
    INTERVAL
    -0.42
     Tax
    -0.42
    POSITIVE LOGITS
    DoubleQuotes
    0.99
     الحره
    0.95
     ब्रेकडाउन
    0.95
    InitVars
    0.94
    Datuak
    0.94
     Roskov
    0.93
    MLLoader
    0.93
    TargetException
    0.90
    sizeCache
    0.88
    IntoConstraints
    0.84
    Activations Density 0.454%

    No Known Activations