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

    Neuronpedia

    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. 8-GEMMASCOPE-RES-16K
    11. 7536
    Prev
    Next
    INDEX
    Explanations

    terms related to secrecy and confidential matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    -1.00
    MigrationBuilder
    -0.96
    PyExc
    -0.90
    NameInMap
    -0.90
    ✨:
    -0.88
    EndTag
    -0.74
    Fuckin
    -0.73
    addPreferredGap
    -0.73
     FontWeight
    -0.70
    expandindo
    -0.69
    POSITIVE LOGITS
     Secret
    2.01
    Secret
    1.97
     secret
    1.95
     SECRET
    1.92
     secrets
    1.85
    secret
    1.82
     Secrets
    1.79
    SECRET
    1.60
    Secrets
    1.56
    secrets
    1.52
    Activations Density 0.086%

    No Known Activations