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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1660
    Prev
    Next
    INDEX
    Explanations

    percentages in various contexts

    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
    談社
    -1.00
     roulant
    -0.91
    AutoScaleMode
    -0.85
    OGND
    -0.83
    Zeneca
    -0.83
     Dundas
    -0.83
     épais
    -0.82
    jasama
    -0.82
    ^(@)
    -0.82
     Bk
    -0.81
    POSITIVE LOGITS
    en
    0.86
     Chaudh
    0.79
    ness
    0.79
     Prozent
    0.77
    ations
    0.75
    ią
    0.75
    ís
    0.75
     percent
    0.74
    ation
    0.73
     ciento
    0.71
    Activations Density 0.138%

    No Known Activations