© 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 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. 83049
    Prev
    Next
    INDEX
    Explanations

    references to various kinds of items

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

    listing of items

    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
     TextInputType
    -0.73
    󠁮
    -0.57
     hydrostatic
    -0.55
     forState
    -0.53
    raulic
    -0.53
    expectations
    -0.50
     McLaughlin
    -0.50
     useAuth
    -0.50
     electrostatic
    -0.49
     Geophysics
    -0.49
    POSITIVE LOGITS
     items
    1.81
     Items
    1.56
     item
    1.50
    items
    1.44
    Items
    1.40
     ITEMS
    1.35
     Item
    1.24
    Item
    1.21
    ITEMS
    1.11
     ITEM
    1.09
    Activations Density 0.018%

    No Known Activations