© 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. 19813
    Prev
    Next
    INDEX
    Explanations

    language indicative of casualness and nonchalance in communication

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

    low-key, quiet, discreet

    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
    currentColor
    -0.34
     cintas
    -0.32
    แตก
    -0.28
     jesu
    -0.27
     wireType
    -0.27
     présidenti
    -0.27
     Jesu
    -0.27
     szklan
    -0.27
    LookAnd
    -0.26
    úsqueda
    -0.26
    POSITIVE LOGITS
     quietly
    0.79
    quiet
    0.78
    tagHelperRunner
    0.75
    Quiet
    0.73
     initComponents
    0.72
    地味
    0.71
    低调
    0.71
    cognito
    0.70
     Quiet
    0.67
     quiet
    0.66
    Activations Density 0.008%

    No Known Activations