© 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
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7727
    Prev
    Next
    INDEX
    Explanations

    key moments and events in a sports context

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

    halves or parts of a whole

    np_acts-logits-general · gemini-2.0-flash

    game periods and halves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ää
    -0.41
     Escolar
    -0.41
     anún
    -0.39
    före
    -0.38
    Numéro
    -0.38
    WriteAttribute
    -0.36
     beroep
    -0.36
    æder
    -0.35
    Couleur
    -0.35
    tagHelperRunner
    -0.34
    POSITIVE LOGITS
     halftime
    0.84
    前半
    0.69
     half
    0.64
    後半
    0.62
     Hälfte
    0.56
    half
    0.56
    ハーフ
    0.55
     inning
    0.55
     Half
    0.54
    Half
    0.54
    Activations Density 0.103%

    No Known Activations