© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 11007
    Prev
    Next
    INDEX
    Explanations

    references to specific seasons and their associated events in sports

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

    Year/number followed by season or school

    np_acts-logits-general · gemini-2.0-flash

    fiscal year and season

    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
    msgTypes
    -0.71
     autorytatywna
    -0.68
     يتيمه
    -0.58
    Personendaten
    -0.57
     wireType
    -0.56
     scoperto
    -0.52
    apimachinery
    -0.51
    dflare
    -0.50
     Paglinawan
    -0.50
    Cartney
    -0.49
    POSITIVE LOGITS
     season
    0.68
    season
    0.57
     fiscal
    0.55
     stagione
    0.52
     seasons
    0.52
     Season
    0.52
    Season
    0.50
     saison
    0.49
    fiscal
    0.48
     FY
    0.47
    Activations Density 0.211%

    No Known Activations