© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 84198
    Prev
    Next
    INDEX
    Explanations

    terms related to facial recognition and biometric data

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

    biometric recognition and speech processing

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ReusableCell
    -0.46
    ronpa
    -0.38
     bet
    -0.38
     stepping
    -0.34
     Provisions
    -0.34
    LookAnd
    -0.34
    TemporalType
    -0.33
     Program
    -0.33
    AnimationsModule
    -0.33
     Programs
    -0.33
    POSITIVE LOGITS
     ainfi
    0.64
    Facial
    0.64
     facial
    0.63
     biometric
    0.61
     Facial
    0.58
    OGND
    0.57
    facial
    0.56
     visage
    0.54
    nologie
    0.54
     Verſ
    0.54
    Activations Density 0.010%

    No Known Activations