© 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. 82940
    Prev
    Next
    INDEX
    Explanations

    the use of action-related verbs, particularly those referring to movement or change

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

    movement or being moved

    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
    featureID
    -0.71
    TagMode
    -0.69
    parsedMessage
    -0.66
    曖昧さ回避
    -0.65
    ScopeManager
    -0.65
     HasFactory
    -0.63
     tiguan
    -0.63
     BrowserModule
    -0.62
    enderror
    -0.60
    AndEndTag
    -0.60
    POSITIVE LOGITS
     Mover
    0.53
    動
    0.51
     mover
    0.51
    moving
    0.50
     moving
    0.49
     movers
    0.48
     Movers
    0.48
     immovable
    0.48
    动
    0.45
     moved
    0.44
    Activations Density 0.065%

    No Known Activations