© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 101825
    Prev
    Next
    INDEX
    Explanations

    references to somatic concepts, particularly related to cells, symptoms, and desires associated with physicality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    cells and mutations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     وتسجيلات
    -0.48
    crumbs
    -0.47
    PyExc
    -0.47
    Chham
    -0.46
     ligiloj
    -0.45
     endwhile
    -0.45
    MigrationBuilder
    -0.44
    withIdentifier
    -0.44
    ValueStyle
    -0.43
    govine
    -0.43
    POSITIVE LOGITS
     somatic
    0.44
    MessageTagHelper
    0.35
     worldly
    0.35
    RenderAtEndOf
    0.34
     Secular
    0.33
     secular
    0.33
    ValueGeneration
    0.32
     arreg
    0.31
    Biographie
    0.30
    openhauer
    0.30
    Activations Density 0.112%

    No Known Activations