© 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. 16677
    Prev
    Next
    INDEX
    Explanations

    specific types of statistics and classifications related to various subjects

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

    official projects and named entities

    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
     AssemblyCulture
    -0.80
    webElementXpaths
    -0.78
    oredCriteria
    -0.77
     Taktlose
    -0.75
    RenderAtEndOf
    -0.75
    tagHelperRunner
    -0.72
     jspb
    -0.71
     &___
    -0.71
    تقاوى
    -0.70
    OGND
    -0.70
    POSITIVE LOGITS
    กาย
    0.44
     administration
    0.42
     Schen
    0.42
     Ver
    0.41
     analysis
    0.41
    面的
    0.40
     Kline
    0.39
    違って
    0.39
     official
    0.38
     Project
    0.38
    Activations Density 0.120%

    No Known Activations