© 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. 55855
    Prev
    Next
    INDEX
    Explanations

    references to events or significant actions within a text

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

    section titles

    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
    AndEndTag
    -0.70
     ब्रेकडाउन
    -0.58
     Савезне
    -0.56
    تقاوى
    -0.55
     arşivlendi
    -0.55
    thâu
    -0.55
     Taktlose
    -0.52
    CROSSTALK
    -0.50
    tanleria
    -0.49
     لينك
    -0.48
    POSITIVE LOGITS
    DockStyle
    0.59
    LookAnd
    0.53
    .*")]
    0.40
     entr
    0.37
     понравилось
    0.34
    DispatchToProps
    0.33
     abond
    0.33
    شویی
    0.33
    elemField
    0.33
      (
    0.32
    Activations Density 0.112%

    No Known Activations