© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 58866
    Prev
    Next
    INDEX
    Explanations

    symbols and characters typically used in mathematical or scientific contexts

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

    acterial abbreviations

    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
    .
    -0.39
     connaissances
    -0.38
     afectados
    -0.35
     particulières
    -0.30
     manières
    -0.30
     conclusión
    -0.29
     âmes
    -0.28
     derniers
    -0.28
     involucrados
    -0.28
     anledning
    -0.28
    POSITIVE LOGITS
    ſelf
    0.81
     HasFactory
    0.77
     ſei
    0.76
    leſs
    0.75
    niſſe
    0.75
    verwijspagina
    0.74
     ſta
    0.73
    ſicht
    0.73
    <unused23>
    0.73
    <unused16>
    0.72
    Activations Density 0.129%

    No Known Activations