© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 42651
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to biological structures and mechanisms

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    low to high

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    帖最后由
    -0.56
    ScopeManager
    -0.55
     nakalista
    -0.54
     ModelExpression
    -0.52
     AssemblyCulture
    -0.51
     ujednoznacz
    -0.49
    󠁬
    -0.49
     transférez
    -0.47
    styleType
    -0.47
     المعيارى
    -0.46
    POSITIVE LOGITS
    exitRule
    0.45
     exceptionnelle
    0.36
     hohe
    0.35
     VERY
    0.35
    accro
    0.34
    seem
    0.34
     very
    0.33
    prä
    0.33
     semble
    0.33
    govor
    0.33
    Activations Density 0.114%

    No Known Activations