© 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
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 7328
    Prev
    Next
    INDEX
    Explanations

    phrases related to the organization and classification of information and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INTO
    -0.79
    Into
    -0.79
     onto
    -0.76
     INTO
    -0.73
     Into
    -0.69
    into
    -0.68
    onto
    -0.59
    FROM
    -0.57
    ABOUT
    -0.56
    THROUGH
    -0.52
    POSITIVE LOGITS
     EconPapers
    0.66
    ulemon
    0.66
     inte
    0.58
     int
    0.58
    Hochspringen
    0.56
    aarrggbb
    0.55
    providedIn
    0.55
     disambiguazione
    0.54
    تقاوى
    0.53
    -------------</
    0.50
    Activations Density 0.197%

    No Known Activations