© 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. 37-GEMMASCOPE-RES-16K
    6. 5599
    Prev
    Next
    INDEX
    Explanations

    ratings and scores for various products or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    хьтан
    -0.46
    zość
    -0.44
    esgue
    -0.39
    quisar
    -0.38
    richTextPanel
    -0.36
    Announcements
    -0.35
    turnstile
    -0.35
    phosa
    -0.35
    setOnAction
    -0.34
     InputDecoration
    -0.34
    POSITIVE LOGITS
     rating
    2.31
     ratings
    2.00
     Rating
    1.97
     RATING
    1.82
    Rating
    1.79
    rating
    1.78
     Ratings
    1.74
     rated
    1.70
    ratings
    1.59
    RATING
    1.55
    Activations Density 0.450%

    No Known Activations