© 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. 13704
    Prev
    Next
    INDEX
    Explanations

    actions and verbs related to movement and progression

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

    move to a direction

    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
    classnames
    -0.50
    yntax
    -0.50
    astéroïdes
    -0.47
    basicConfig
    -0.41
     IconData
    -0.41
    hythm
    -0.40
    malink
    -0.40
    yll
    -0.39
     awakeFromNib
    -0.38
    Sucesor
    -0.38
    POSITIVE LOGITS
     move
    0.93
    move
    0.81
    Move
    0.81
     moves
    0.78
     moved
    0.77
     moving
    0.76
     Move
    0.76
     이동
    0.73
    Moving
    0.73
    moved
    0.71
    Activations Density 0.028%

    No Known Activations