© 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. 1498
    Prev
    Next
    INDEX
    Explanations

    concessive clauses indicating contradiction or contrast

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

    concessive conjunctions

    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
     either
    -0.28
     like
    -0.25
     ones
    -0.25
     empe
    -0.25
     equivalent
    -0.25
     equivale
    -0.25
     ak
    -0.24
     particuli
    -0.24
     equivalente
    -0.24
     because
    -0.24
    POSITIVE LOGITS
    OGND
    0.85
    protoimpl
    0.79
     ब्रेकडाउन
    0.77
    ésultats
    0.72
     queſta
    0.72
    ロウィン
    0.71
    
    0.71
    Personensuche
    0.69
    enablog
    0.69
    niſſe
    0.69
    Activations Density 0.127%

    No Known Activations