© 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. 58884
    Prev
    Next
    INDEX
    Explanations

    words related to brightness or illumination, particularly those indicating something being well-lit or figuratively "lit."

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

    slang for excellent or intense

    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
    enfone
    -0.40
    最快更新
    -0.38
    subpackage
    -0.33
     XHTML
    -0.32
    resizingMask
    -0.32
    addPreferredGap
    -0.31
    IBOutlet
    -0.31
    ECONDS
    -0.30
     reader
    -0.30
    zahn
    -0.29
    POSITIVE LOGITS
     🔥🔥
    0.65
    RTHOOK
    0.61
    🔥🔥
    0.60
     🔥
    0.59
    StoreMessageInfo
    0.58
     GOAT
    0.57
    🔥🔥🔥
    0.56
    🔥
    0.56
     banger
    0.55
     incredible
    0.55
    Activations Density 0.052%

    No Known Activations