© 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. 15171
    Prev
    Next
    INDEX
    Explanations

    references to composite structures or entities within data or text

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

    composite

    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
     veau
    -0.51
    Hora
    -0.50
     cerveau
    -0.50
     חיצוניים
    -0.48
     règne
    -0.47
     FetchType
    -0.47
     horaire
    -0.47
    PhysRevLett
    -0.47
     autorité
    -0.47
     inalámbrica
    -0.46
    POSITIVE LOGITS
     Composite
    2.48
     composite
    2.47
    Composite
    2.44
    composite
    2.23
     COMPOS
    1.58
     composites
    1.50
    COMPOS
    1.36
    composites
    1.30
     Composites
    1.26
    复合
    1.20
    Activations Density 0.006%

    No Known Activations