© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 126208
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Championship" and its variations

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

    sports championship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.51
    er
    -0.48
    AllowUser
    -0.46
    GetAxis
    -0.44
    ')).
    -0.44
    tolerant
    -0.44
     Nere
    -0.44
    lgari
    -0.44
    Toler
    -0.44
    Poli
    -0.44
    POSITIVE LOGITS
     Championship
    0.99
     championship
    0.95
    Championship
    0.86
     championships
    0.86
     Championships
    0.77
     campeonato
    0.70
    atorship
    0.70
    mybatisplus
    0.65
    manship
    0.60
    onatos
    0.60
    Activations Density 0.003%

    No Known Activations