© 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. 7-GEMMASCOPE-RES-16K
    11. 9220
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly relating to Joseph Sanders and his familial connections and history

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 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
     lexer
    -0.95
    :\/\/
    -0.91
     Himal
    -0.91
    thâu
    -0.91
     Matrices
    -0.88
    JTable
    -0.87
     simpson
    -0.87
     photolibrary
    -0.85
     Collingwood
    -0.84
     GNP
    -0.84
    POSITIVE LOGITS
    ••••
    0.71
    providedIn
    0.68
    )|^{
    0.67
    videoId
    0.66
     Wass
    0.64
    prm
    0.63
    hyd
    0.63
     AM
    0.63
    AM
    0.62
     Sheridan
    0.61
    Activations Density 1.955%

    No Known Activations