© 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. 14267
    Prev
    Next
    INDEX
    Explanations

    references to secrets or hidden information

    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
     AspNetCore
    -0.53
    izace
    -0.51
     Washburn
    -0.50
    ナブル
    -0.49
     llantas
    -0.49
    harusnya
    -0.49
     badkamer
    -0.48
    fender
    -0.48
    Rourke
    -0.48
    pides
    -0.47
    POSITIVE LOGITS
     secret
    3.05
    secret
    2.77
    Secret
    2.75
     Secret
    2.75
     SECRET
    2.59
     secrets
    2.38
    SECRET
    2.27
     secreto
    2.16
     Secrets
    2.02
    secrets
    2.02
    Activations Density 0.127%

    No Known Activations