© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 42713
    Prev
    Next
    INDEX
    Explanations

    expressive and impactful visual or emotional descriptors

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

    jaw dropping, eye watering, awe inspiring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Replicas
    -0.38
     امر
    -0.33
     Bec
    -0.33
     enfo
    -0.31
    Resolve
    -0.31
    Resolved
    -0.31
    बार
    -0.31
     Pol
    -0.31
     Secured
    -0.31
    oa̍t
    -0.31
    POSITIVE LOGITS
     shattering
    0.79
     breathtaking
    0.76
    inspiring
    0.71
    stunning
    0.71
     stunning
    0.70
    PropertyChanging
    0.69
     defying
    0.69
     inspiring
    0.69
     astounding
    0.68
    breaking
    0.68
    Activations Density 0.043%

    No Known Activations