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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 8735
    Prev
    Next
    INDEX
    Explanations

    numerical expressions and mathematical operations

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

    Expressions containing "+"

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions involving exponents

    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
    elemField
    -0.53
    copyFrom
    -0.44
    awtextra
    -0.44
    RTLI
    -0.40
    XmlAccessorType
    -0.39
     Kün
    -0.39
    照
    -0.38
    TargetApi
    -0.38
    CppMethod
    -0.37
     Chwiliwch
    -0.37
    POSITIVE LOGITS
     faſt
    0.57
     houſe
    0.52
     pleaſure
    0.50
     raiſ
    0.48
     fubject
    0.48
     Majefty
    0.48
     ſon
    0.47
     AssemblyCulture
    0.47
     ſeveral
    0.46
     ſol
    0.46
    Activations Density 2.973%

    No Known Activations