© 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. 61989
    Prev
    Next
    INDEX
    Explanations

    acronyms and specific codes related to regulatory and operational concepts

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

    cr / acr prefixes

    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
     Informa
    -0.50
     Hayward
    -0.46
    idated
    -0.46
    getUserInfo
    -0.44
    uesta
    -0.44
    AGGIO
    -0.43
    なぎ
    -0.43
     informa
    -0.43
     Maitland
    -0.43
    IPPED
    -0.43
    POSITIVE LOGITS
    cr
    0.96
    CR
    0.91
    cri
    0.86
    ACR
    0.84
    CRI
    0.84
    cry
    0.82
     CR
    0.77
    cre
    0.76
    Cr
    0.76
    cro
    0.76
    Activations Density 0.057%

    No Known Activations