© 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. 31-GEMMASCOPE-RES-131K
    6. 65245
    Prev
    Next
    INDEX
    Explanations

    specific food items and their ingredients in a recipe context

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

    surrounded

    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
     initComponents
    -0.49
    ={({
    -0.39
    Ehrungen
    -0.36
     involucra
    -0.36
     semula
    -0.35
     tamén
    -0.35
     antaranya
    -0.35
     ruines
    -0.34
     sekal
    -0.32
     fidé
    -0.32
    POSITIVE LOGITS
     surrounded
    1.34
     accompanied
    1.27
     flanked
    1.13
    accompanied
    1.05
     paired
    1.05
     complemented
    1.00
     followed
    0.98
     coupled
    0.97
    companied
    0.96
     preceded
    0.95
    Activations Density 0.210%

    No Known Activations