© 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. 29268
    Prev
    Next
    INDEX
    Explanations

    action-oriented phrases and expressions related to functionality and application

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

    act to do something

    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
     betweenstory
    -0.90
    transQ
    -0.68
    SequentialGroup
    -0.66
     MainAxisSize
    -0.66
    featureID
    -0.64
    setVerticalGroup
    -0.60
    BibitemShut
    -0.59
     wireType
    -0.57
    sizeCache
    -0.55
    protetor
    -0.53
    POSITIVE LOGITS
    ValueStyle
    0.35
    bench
    0.33
    toMatch
    0.32
    はじめに
    0.31
    anz
    0.31
    griffe
    0.31
     Fu
    0.31
     serem
    0.31
    fu
    0.30
     rem
    0.30
    Activations Density 0.068%

    No Known Activations