© 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
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 7522
    Prev
    Next
    INDEX
    Explanations

    code snippets related to data manipulation and filtering in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.42
    TestingModule
    -0.41
     مشين
    -0.41
    Portail
    -0.38
    Географиясе
    -0.35
     luas
    -0.33
    Collegamenti
    -0.31
    ㅂ
    -0.31
    ęki
    -0.30
     Verkehr
    -0.30
    POSITIVE LOGITS
     row
    2.97
     Row
    2.58
     rows
    2.50
    row
    2.48
    Row
    2.45
     Rows
    2.20
     ROW
    2.19
    ROW
    2.02
    rows
    1.97
    Rows
    1.95
    Activations Density 0.788%

    No Known Activations