© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 11568
    Prev
    Next
    INDEX
    Explanations

    commands related to saving data or preferences

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

    saving files or data

    np_acts-logits-general · gemini-2.0-flash

    saving data and files

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     pageIndex
    -0.47
     deltag
    -0.44
     Urbano
    -0.44
     tunt
    -0.43
     circon
    -0.42
    træ
    -0.42
    FunctionType
    -0.42
    ElementType
    -0.42
    UnknownFields
    -0.42
    RuleContext
    -0.42
    POSITIVE LOGITS
     save
    2.19
    save
    2.17
    Save
    2.05
     Save
    2.02
     saving
    1.96
     saves
    1.91
    saving
    1.88
     SAVE
    1.88
    SAVE
    1.84
     Saving
    1.83
    Activations Density 0.069%

    No Known Activations