© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 84840
    Prev
    Next
    INDEX
    Explanations

    mentions of specific football players and their achievements

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

    English footballers

    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
    esModule
    -0.45
    scriptcase
    -0.38
    不住
    -0.35
    MENAFN
    -0.35
    θεν
    -0.35
     World
    -0.34
     world
    -0.34
     Sato
    -0.34
     Ketten
    -0.33
     Hansen
    -0.32
    POSITIVE LOGITS
     Rashford
    0.69
     Lampard
    0.68
    england
    0.63
    England
    0.63
     england
    0.61
     ENGLAND
    0.60
    rungsseite
    0.58
    appé
    0.58
    afone
    0.58
    Zeneca
    0.58
    Activations Density 0.007%

    No Known Activations