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. 7-GEMMASCOPE-RES-16K
    6. 8671
    Prev
    Next
    INDEX
    Explanations

    occurrences of dialogue and reported speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yns
    -0.60
    jsdelivr
    -0.58
     /\.(
    -0.56
    ablemente
    -0.56
     PL
    -0.54
    yn
    -0.54
    Beste
    -0.54
    writeValue
    -0.53
    стта
    -0.53
    )}_{
    -0.53
    POSITIVE LOGITS
    addContainerGap
    0.92
    ValueStyle
    0.84
    DoubleQuotes
    0.78
    HtmlAttribute
    0.69
     مشين
    0.68
    脚注の使い方
    0.67
     initComponents
    0.66
    basicConfig
    0.66
     Dijo
    0.62
    reactstrap
    0.61
    Activations Density 0.044%

    No Known Activations