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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 999
    Prev
    Next
    INDEX
    Explanations

    the beginning of new sections or topics in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.93
    principalColumn
    -0.89
    下载附件
    -0.86
    windowFixed
    -0.84
     архивлан
    -0.83
    IndentedString
    -0.82
    ArgsConstructor
    -0.81
    })`
    -0.78
    TintMode
    -0.78
    FunctionFlags
    -0.77
    POSITIVE LOGITS
     跳转至
    0.60
    seamnă
    0.60
    <h3>
    0.58
    <table>
    0.54
    lardır
    0.53
    <h1>
    0.51
     plegable
    0.50
    providedIn
    0.47
    Gdx
    0.46
     compétences
    0.44
    Activations Density 3.595%

    No Known Activations