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-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5823
    Prev
    Next
    INDEX
    Explanations

    announcements or declarations related to events or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AppMethodBeat
    -0.55
     either
    -0.39
    TacToe
    -0.36
    AnchorStyles
    -0.36
     entstand
    -0.34
     autant
    -0.34
     currently
    -0.33
     nonUne
    -0.33
     Begründung
    -0.33
    はもちろん
    -0.33
    POSITIVE LOGITS
     plans
    0.95
    plans
    0.85
     PLANS
    0.75
     Pläne
    0.75
    Plans
    0.73
     Plans
    0.73
    liminary
    0.71
     preliminary
    0.69
     revisions
    0.66
     planos
    0.66
    Activations Density 0.694%

    No Known Activations