Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 40092
    Prev
    Next
    INDEX
    Explanations

    occurrences of parentheses and related syntax characters in code

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

    function calls and callbacks

    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
    AsUp
    -0.42
    astéroïdes
    -0.36
     continuará
    -0.35
    ckså
    -0.35
     hoạch
    -0.35
    verifyException
    -0.34
     Within
    -0.32
     tambin
    -0.31
    PreferredItem
    -0.30
     plads
    -0.30
    POSITIVE LOGITS
     astore
    0.83
     istore
    0.58
    WithMany
    0.57
    AddTagHelper
    0.53
    GOTREF
    0.52
     AttributeSet
    0.52
    ="@+
    0.50
    jsxFileName
    0.50
     kasarigan
    0.49
     consultato
    0.48
    Activations Density 0.012%

    No Known Activations