© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 57114
    Prev
    Next
    INDEX
    Explanations

    phrases related to prompting actions or decisions

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

    leading to future actions

    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
    पया
    -0.50
     Independencia
    -0.34
     Shakspeare
    -0.33
    complexType
    -0.32
    Amicalement
    -0.31
    ESIS
    -0.31
    Dislikes
    -0.31
     industrielle
    -0.31
     Turquía
    -0.30
     gew
    -0.30
    POSITIVE LOGITS
    rungsseite
    0.68
    .*")]
    0.68
     ब्रेकडाउन
    0.65
    webElementXpaths
    0.62
    hyrchwyd
    0.58
    الحياه
    0.57
    帖最后由
    0.54
    enderror
    0.54
    ThemeOverlay
    0.53
     GenerationType
    0.52
    Activations Density 0.102%

    No Known Activations