© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 12768
    Prev
    Next
    INDEX
    Explanations

    elements related to sports events and competitive outcomes

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

    scores or leads in a game

    np_acts-logits-general · gemini-2.0-flash

    score preceding numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zzleHttp
    -0.68
     ujednoznacz
    -0.66
     ***!
    -0.61
    躇
    -0.61
     aveug
    -0.60
    olisian
    -0.59
    UrlResolution
    -0.58
     chiare
    -0.57
     rispar
    -0.56
    出版年
    -0.55
    POSITIVE LOGITS
     score
    1.21
     scores
    1.02
     Score
    0.98
    Score
    0.94
    score
    0.94
     scored
    0.92
     scoring
    0.85
     Scores
    0.84
    Scores
    0.78
     SCORE
    0.76
    Activations Density 0.160%

    No Known Activations