© 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. 20548
    Prev
    Next
    INDEX
    Explanations

    sections containing instructions or descriptions in a structured format

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

    foreign language text

    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
    ſicht
    -0.82
    majánló
    -0.81
    niſſe
    -0.76
     zwiſchen
    -0.75
    нгред
    -0.74
    ſammen
    -0.73
    ſehen
    -0.72
     ſehen
    -0.71
     ſeyn
    -0.70
    <unused17>
    -0.70
    POSITIVE LOGITS
     nahilalakip
    0.34
     constitucional
    0.30
     zák
    0.28
     werkzaam
    0.28
     arbete
    0.28
     hogares
    0.28
     grunn
    0.28
     niets
    0.26
     fossero
    0.26
     niega
    0.26
    Activations Density 0.000%

    No Known Activations