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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105552
    Prev
    Next
    INDEX
    Explanations

    key terms related to emphasis and the concept of identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ویکی‌پدی
    -0.53
    ILA
    -0.42
    「
    -0.37
     autorytatywna
    -0.36
     unacc
    -0.36
    IFI
    -0.35
    pada
    -0.34
    //};
    -0.34
    【
    -0.34
    ●
    -0.34
    POSITIVE LOGITS
    TypedDataSet
    0.61
    ロウィン
    0.57
    久しぶ
    0.57
    iſche
    0.56
    enablog
    0.56
    <unused79>
    0.55
    <unused80>
    0.55
    <unused68>
    0.55
    [@BOS@]
    0.55
    <unused17>
    0.55
    Activations Density 0.036%

    No Known Activations