© 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. 25-GEMMASCOPE-RES-16K
    6. 15454
    Prev
    Next
    INDEX
    Explanations

    sports-related content, specifically highlighting performance and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     metast
    -0.45
    éez
    -0.44
    TAWA
    -0.43
     subtropical
    -0.42
    assertj
    -0.40
     milliard
    -0.40
    dersfield
    -0.40
    __*/
    -0.40
     ducati
    -0.39
     bilinear
    -0.39
    POSITIVE LOGITS
     girls
    0.69
     varsity
    0.61
     Girls
    0.60
     Schülern
    0.60
    Girls
    0.57
     junior
    0.56
    girls
    0.55
     Junior
    0.55
     Schüler
    0.54
     boys
    0.54
    Activations Density 0.156%

    No Known Activations