© 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. 122588
    Prev
    Next
    INDEX
    Explanations

    open and close brackets or braces

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

    label for equations

    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
     bezeichneter
    -0.50
    bcryptjs
    -0.40
    تقاوى
    -0.40
    탤
    -0.38
    insics
    -0.35
    AdapterFactory
    -0.35
    strconv
    -0.35
    erialization
    -0.34
    appspot
    -0.34
    ftagPool
    -0.33
    POSITIVE LOGITS
     AssemblyTitle
    0.68
    setVerticalGroup
    0.64
    <caption>
    0.59
     surla
    0.55
    __(/*!
    0.52
     Houſe
    0.52
    Життєпис
    0.51
    Paper
    0.50
    IContainer
    0.50
     Titre
    0.49
    Activations Density 0.002%

    No Known Activations