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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 13498
    Prev
    Next
    INDEX
    Explanations

    statistics related to baseball performance

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

    Numbers followed by baseball statistics

    np_acts-logits-general · gemini-2.0-flash

    numbers of runs and hits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.65
    IntoConstraints
    -0.62
     createState
    -0.59
    horesis
    -0.59
    spesies
    -0.57
     teilnehmen
    -0.56
    ьаж
    -0.55
    gnose
    -0.53
    localctx
    -0.52
    pto
    -0.52
    POSITIVE LOGITS
     runs
    0.85
     hits
    0.85
     walks
    0.79
     earned
    0.78
     Runs
    0.76
     Earned
    0.72
    runs
    0.70
    earned
    0.70
     run
    0.69
     Hits
    0.69
    Activations Density 0.161%

    No Known Activations