© 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. 20-GEMMASCOPE-RES-131K
    11. 73511
    Prev
    Next
    INDEX
    Explanations

    cooking measurements and ingredient quantities

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

    recipe measurements

    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
     serez
    -0.43
     protoimpl
    -0.37
    AppMethodBeat
    -0.37
     coû
    -0.36
    EndContext
    -0.36
     Picchu
    -0.36
    yntaxException
    -0.35
    calça
    -0.35
    cciale
    -0.35
    Demografia
    -0.35
    POSITIVE LOGITS
     tablespoons
    1.02
     tablespoon
    0.96
     Tbsp
    0.87
     tbsp
    0.82
     cucchiaio
    0.70
     teaspoons
    0.69
    Spoon
    0.67
     teaspoon
    0.67
     spoon
    0.64
     Spoon
    0.63
    Activations Density 0.003%

    No Known Activations