© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 11615
    Prev
    Next
    INDEX
    Explanations

    terms related to secrecy and confidential information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     становника
    -0.93
    NameInMap
    -0.86
    MigrationBuilder
    -0.76
    addPreferredGap
    -0.74
    ✨:
    -0.72
    homonymie
    -0.72
    揄
    -0.70
     surla
    -0.69
    ffichage
    -0.69
    boldsymbol
    -0.68
    POSITIVE LOGITS
     Secret
    1.76
     SECRET
    1.75
    Secret
    1.74
     secret
    1.63
     Secrets
    1.62
     secrets
    1.61
    secret
    1.56
    SECRET
    1.46
    Secrets
    1.45
    secrets
    1.36
    Activations Density 0.116%

    No Known Activations