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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 7548
    Prev
    Next
    INDEX
    Explanations

    phrases and references related to terms and conditions

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

    "terms" appearing in various contexts

    np_acts-logits-general · gemini-2.0-flash

    terms of agreement or mathematics

    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
    <tbody>
    -0.68
     doPost
    -0.58
    Bibliographie
    -0.57
    🏻
    -0.56
     provato
    -0.56
    chappement
    -0.55
    stopwatch
    -0.55
    Frey
    -0.55
    lacian
    -0.54
     الاطلاع
    -0.52
    POSITIVE LOGITS
     terms
    0.99
     Terms
    0.97
     TERM
    0.95
     Term
    0.91
    Terms
    0.88
    terms
    0.86
     TERMS
    0.85
    PreferredItem
    0.81
     Ters
    0.78
    Term
    0.78
    Activations Density 0.151%

    No Known Activations