© 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. 1706
    Prev
    Next
    INDEX
    Explanations

    phrases indicating presence or quantity in relation to entities or actions

    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
     parlor
    -0.78
     igång
    -0.74
    jspx
    -0.73
     Ovid
    -0.73
     profonde
    -0.73
     Cæsar
    -0.71
     Würzburg
    -0.71
    hingga
    -0.70
     Longfellow
    -0.69
    pielt
    -0.68
    POSITIVE LOGITS
     Bure
    0.75
     للمعارف
    0.72
     Schme
    0.70
     Healey
    0.67
    міні
    0.65
     تضيفلها
    0.64
    lès
    0.64
    lanation
    0.63
    ndose
    0.63
     Chees
    0.62
    Activations Density 0.067%

    No Known Activations