© 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. 41529
    Prev
    Next
    INDEX
    Explanations

    instances of telephone-related actions and interactions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    closing and slamming actions

    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
    Negative Logits
    Източници
    -0.53
    GeneratedValue
    -0.49
     ModelExpression
    -0.46
    ponses
    -0.41
    ThroughAttribute
    -0.41
    mjs
    -0.40
    uja
    -0.40
    ForKey
    -0.39
    beforeEach
    -0.39
     Fass
    -0.38
    POSITIVE LOGITS
    verwijspagina
    0.42
     slammed
    0.40
     slamming
    0.40
     Paglinawan
    0.40
     slam
    0.39
    closedir
    0.39
     виправивши
    0.38
     Gegenteil
    0.38
     closed
    0.36
    adaptiveStyles
    0.36
    Activations Density 0.043%

    No Known Activations