© 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. 90804
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to specific cultural references, organizations, and locations

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

    German compound nouns

    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
     Kulit
    -0.78
    schrank
    -0.72
     Kleid
    -0.69
     propOrder
    -0.69
    oa̍t
    -0.69
     Geben
    -0.68
    kissen
    -0.66
     Putih
    -0.64
     plumas
    -0.63
     Kriege
    -0.63
    POSITIVE LOGITS
     reserv
    0.48
     Original
    0.45
     ende
    0.45
     dyna
    0.43
     ver
    0.42
     sympath
    0.42
     bre
    0.42
     ferti
    0.39
     gro
    0.39
     moti
    0.39
    Activations Density 0.095%

    No Known Activations