© 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. 31703
    Prev
    Next
    INDEX
    Explanations

    references to grammar and its rules

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

    language grammar and syntax

    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
    expandindo
    -0.49
    tôi
    -0.46
    ⓘ
    -0.44
     חיצוניים
    -0.44
     putative
    -0.43
    unique
    -0.42
    Neal
    -0.41
    i
    -0.41
     unique
    -0.41
    xnn
    -0.41
    POSITIVE LOGITS
     grammar
    1.23
     Grammar
    1.21
    Grammar
    1.15
    grammar
    1.05
     gramm
    0.85
     grammatical
    0.81
     GRAM
    0.72
    语法
    0.70
     Gramm
    0.66
     syntax
    0.65
    Activations Density 0.004%

    No Known Activations