© 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. 9-GEMMASCOPE-RES-131K
    11. 115239
    Prev
    Next
    INDEX
    Explanations

    references to divine or authoritative figures, along with accolades or titles

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

    titles and achievements

    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
     CURIAM
    -0.69
     nonUne
    -0.63
    IntoConstraints
    -0.61
     Италијани
    -0.56
     Catawiki
    -0.55
    stino
    -0.52
    LookAnd
    -0.52
     drewni
    -0.51
    kabau
    -0.51
    oa̍t
    -0.50
    POSITIVE LOGITS
     competition
    0.32
    !("{
    0.32
    期刊论文
    0.29
     certification
    0.29
     compét
    0.28
     Olympic
    0.28
     olymp
    0.28
    Vegeu
    0.28
    ✎
    0.27
     iron
    0.27
    Activations Density 0.152%

    No Known Activations