Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 102680
    Prev
    Next
    INDEX
    Explanations

    statistical terms and metrics related to sports performance

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

    baseball pitcher and goalkeeper

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    󠀠
    -0.77
    ſſung
    -0.76
    niſſe
    -0.73
     queſto
    -0.73
    нгред
    -0.71
     imagui
    -0.70
    iſen
    -0.70
    ſelben
    -0.70
    <unused17>
    -0.69
    <unused51>
    -0.69
    POSITIVE LOGITS
     pitcher
    0.43
     pitchers
    0.43
     pitching
    0.37
     goalkeeper
    0.35
     bul
    0.30
     Pitcher
    0.27
    photobucket
    0.27
     pitched
    0.27
     loc
    0.27
     channel
    0.26
    Activations Density 0.058%

    No Known Activations