© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 9863
    Prev
    Next
    INDEX
    Explanations

    historical and legal references connected to governance and jurisdiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seton
    -0.88
     Sepp
    -0.87
     Diogo
    -0.85
     Zij
    -0.85
     Pott
    -0.82
    endphp
    -0.79
    ARGS
    -0.78
     Haig
    -0.78
     Scopus
    -0.76
     Sich
    -0.74
    POSITIVE LOGITS
    Bres
    0.86
     createSprite
    0.82
    GraphicsUnit
    0.79
    ्रा
    0.77
     Fre
    0.76
     straws
    0.76
     skr
    0.75
     Frazier
    0.74
     Br
    0.73
     BRE
    0.71
    Activations Density 10.714%

    No Known Activations