© 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. 21631
    Prev
    Next
    INDEX
    Explanations

    references to instructions or functions related to programming or configuration

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

    numbers and code context

    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
     Administrativna
    -0.55
     Савезне
    -0.52
    rrggbb
    -0.43
    盟
    -0.42
    цездатний
    -0.40
     Biôgrafia
    -0.39
     officio
    -0.39
     مرئيه
    -0.38
     ivelany
    -0.37
     屋根
    -0.37
    POSITIVE LOGITS
     nakalista
    0.56
     ***!
    0.51
    !*\
    0.48
    новниш
    0.47
    centralwidget
    0.47
    úgó
    0.45
    IANGLES
    0.45
    ReusableCell
    0.44
    InputBorder
    0.43
    VYMaps
    0.43
    Activations Density 0.142%

    No Known Activations