© 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. 100796
    Prev
    Next
    INDEX
    Explanations

    references to a specific mechanical component related to bolts

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

    bolt or bolts

    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
    ngrx
    -0.54
     disambiguazione
    -0.51
     MenuView
    -0.50
     الرياضيه
    -0.49
     Merriam
    -0.48
    المكان
    -0.48
    BibitemShut
    -0.48
     ویکی‌پدی
    -0.47
    RequestMethod
    -0.47
     Yorkshire
    -0.46
    POSITIVE LOGITS
     bolt
    2.16
     Bolt
    2.03
    Bolt
    1.90
    bolt
    1.88
     bolts
    1.86
     Bolts
    1.64
    bolts
    1.53
     bolted
    1.32
    ボルト
    1.25
     BOL
    1.08
    Activations Density 0.004%

    No Known Activations