© 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-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 14085
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports scores and game outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rshire
    -0.56
    andina
    -0.49
     object
    -0.49
    část
    -0.48
     combineReducers
    -0.48
     recommendation
    -0.48
    @[
    -0.47
     powders
    -0.46
     ఉన్న
    -0.46
     uska
    -0.45
    POSITIVE LOGITS
    SequentialGroup
    0.71
     estekak
    0.70
    ValueStyle
    0.65
    onomía
    0.61
    enumi
    0.61
     BeautifulSoup
    0.60
     @"/
    0.60
    thâu
    0.58
    хьтан
    0.58
    XmlEnum
    0.57
    Activations Density 0.094%

    No Known Activations