© 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. 127026
    Prev
    Next
    INDEX
    Explanations

    proper nouns, names, and specific identifiers

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

    specific names and identifiers

    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
    ://
    -0.28
    legung
    -0.23
     دا
    -0.23
     an
    -0.22
    先
    -0.22
    ↵↵
    -0.22
     
    -0.21
    AttributeSet
    -0.21
     ta
    -0.20
     ut
    -0.20
    POSITIVE LOGITS
    tanleria
    0.83
     ProtoMessage
    0.79
    󠀠
    0.75
    featureID
    0.75
    SharedDtor
    0.73
     للاسماء
    0.72
    iſen
    0.72
     Monfieur
    0.70
     propOrder
    0.70
    parsedMessage
    0.70
    Activations Density 0.018%

    No Known Activations