© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 115021
    Prev
    Next
    INDEX
    Explanations

    programming variables and data structures

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

    list properties, methods, and values

    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
     cumplimiento
    -0.42
    GetBytes
    -0.39
     homenaje
    -0.39
     conejo
    -0.39
    :^(
    -0.38
    offsetof
    -0.37
     zaj
    -0.36
     contribución
    -0.36
     jūsų
    -0.36
     exécu
    -0.36
    POSITIVE LOGITS
    addPreferredGap
    0.66
     MainAxisSize
    0.63
    IntoConstraints
    0.61
    tableFuture
    0.58
    RTHOOK
    0.58
    SequentialGroup
    0.58
    SharedCtor
    0.57
    oredCriteria
    0.57
    AxisAlignment
    0.57
    ConstraintMaker
    0.57
    Activations Density 0.011%

    No Known Activations