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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 13480
    Prev
    Next
    INDEX
    Explanations

    references to product features, specifications, and user experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.56
    ต้น
    -0.39
    chuga
    -0.33
     vorstellen
    -0.32
    appartement
    -0.31
     intercepted
    -0.31
    izon
    -0.31
     Schwartz
    -0.31
     rust
    -0.30
     Marcel
    -0.30
    POSITIVE LOGITS
     Cases
    0.81
    Cases
    0.81
     cases
    0.79
     case
    0.77
    ケース
    0.76
    Case
    0.75
     Case
    0.75
     etui
    0.74
    cases
    0.73
     protective
    0.71
    Activations Density 0.142%

    No Known Activations