© 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. 20-GEMMASCOPE-RES-131K
    11. 115803
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical appearance, particularly related to hair and eye color

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.55
    SharedDtor
    -0.48
     pageable
    -0.48
    pholes
    -0.47
     struts
    -0.47
    RenderAtEndOf
    -0.46
    stunde
    -0.45
     Attitude
    -0.45
    polation
    -0.45
    Cyfarwyddwr
    -0.44
    POSITIVE LOGITS
    Autoritní
    0.38
     brunette
    0.38
    bcryptjs
    0.35
     blonde
    0.33
    jface
    0.32
    XMLSchema
    0.31
    posedge
    0.31
     PropTypes
    0.31
     vVar
    0.31
     Schmel
    0.30
    Activations Density 0.006%

    No Known Activations