© 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. 31-GEMMASCOPE-RES-131K
    11. 8538
    Prev
    Next
    INDEX
    Explanations

    scientific terminology and quantitative relationships

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

    rankings and hierarchies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    mapStateToProps
    -0.45
    EDEFAULT
    -0.40
     anniversaire
    -0.40
    Repeated
    -0.39
     nuages
    -0.39
    InputBorder
    -0.39
    akterysty
    -0.38
    enterOuterAlt
    -0.38
    emplares
    -0.37
     Instrumentation
    -0.36
    POSITIVE LOGITS
     hierarchy
    1.79
     hierarchies
    1.47
     Hierarchy
    1.45
    hierarchy
    1.38
     ranking
    1.37
     hiér
    1.37
     hierarchical
    1.34
     rankings
    1.28
    Hierarchy
    1.25
     hierarch
    1.24
    Activations Density 0.092%

    No Known Activations