© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 12990
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries, particularly those beginning with "why."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AppBundle
    -0.50
     GCM
    -0.50
    Boas
    -0.47
     NSM
    -0.47
    bootstrapcdn
    -0.46
    dataclass
    -0.46
     GSC
    -0.46
     Seva
    -0.46
    GCM
    -0.45
    providedIn
    -0.45
    POSITIVE LOGITS
     why
    2.39
     Why
    2.19
    why
    2.14
    Why
    2.13
     WHY
    1.97
    WHY
    1.95
     pourquoi
    1.81
     Pourquoi
    1.73
     Warum
    1.72
     Waarom
    1.67
    Activations Density 0.054%

    No Known Activations