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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6347
    Prev
    Next
    INDEX
    Explanations

    information related to sports statistics and achievements

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

    Sports, tournaments, and games

    np_acts-logits-general · gemini-2.0-flash

    sports results and tournaments

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     laiko
    -0.32
     شعب
    -0.31
    طبيق
    -0.30
    undaki
    -0.29
    DockStyle
    -0.29
    دانشنامهٔ
    -0.28
    ListComponent
    -0.28
    colgante
    -0.28
     subsidi
    -0.27
     chậm
    -0.27
    POSITIVE LOGITS
     disambiguazione
    0.88
    ScopeManager
    0.66
    featureID
    0.65
     EconPapers
    0.64
     GenerationType
    0.60
    WEBPACK
    0.55
    GraphicsUnit
    0.54
     Paglinawan
    0.54
    complexContent
    0.54
    kegaard
    0.52
    Activations Density 0.140%

    No Known Activations