© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 113488
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions related to agreements and user policies

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

    terms and conditions

    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-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
    帖最后由
    -0.60
    SequentialGroup
    -0.56
    endphp
    -0.54
     ffilmiau
    -0.53
    jsonPath
    -0.53
     BorderSide
    -0.52
    JsonKey
    -0.52
     SearchView
    -0.50
    ⓧ
    -0.49
     geweest
    -0.49
    POSITIVE LOGITS
     conditions
    0.62
     Conditions
    0.61
    ungsbedingungen
    0.55
    Conditions
    0.52
     voorwaarden
    0.51
     CONDITIONS
    0.49
    conditions
    0.49
     terms
    0.47
    waarden
    0.47
     ketentuan
    0.46
    Activations Density 0.008%

    No Known Activations