© 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. 31-GEMMASCOPE-RES-131K
    6. 13206
    Prev
    Next
    INDEX
    Explanations

    mentions of copyright licenses and their usage guidelines

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

    apache license header "you may not"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.50
    invokeLater
    -0.44
    Character
    -0.42
     character
    -0.42
     Unito
    -0.41
     comp
    -0.41
    Kilder
    -0.41
    Искәрмәләр
    -0.41
    pas
    -0.40
    拍
    -0.40
    POSITIVE LOGITS
    hyrchwyd
    0.42
    complexContent
    0.41
     înc
    0.40
     zoude
    0.40
     armées
    0.40
     sebut
    0.39
     <=",
    0.39
    tagHelper
    0.39
    interopRequire
    0.38
     pokrač
    0.38
    Activations Density 0.011%

    No Known Activations