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. 21430
    Prev
    Next
    INDEX
    Explanations

    references to statistics and rankings related to sports and organizations

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

    ranking and superlatives

    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
    ंदीखरीदारी
    -0.33
     karşılaş
    -0.30
     magasiner
    -0.30
    trui
    -0.29
     مل
    -0.28
     soie
    -0.27
     paille
    -0.27
     تضيفلها
    -0.27
     maceta
    -0.26
    épa
    -0.26
    POSITIVE LOGITS
    yntaxException
    0.66
     contextLoads
    0.66
     Normdatei
    0.64
     henvisninger
    0.60
    NameInMap
    0.58
     surla
    0.56
    errHandler
    0.56
     Италијани
    0.55
    verwijs
    0.54
    AndEndTag
    0.54
    Activations Density 0.031%

    No Known Activations