© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 91091
    Prev
    Next
    INDEX
    Explanations

    terms related to focus or concentration in various contexts

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

    verbs related to inclusion, composition, and focus

    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
    出版年
    -0.80
     whoſe
    -0.70
     myſelf
    -0.62
     fubject
    -0.61
     whofe
    -0.61
     poffe
    -0.60
    AnchorTagHelper
    -0.60
    DoubleQuotes
    -0.59
     himſelf
    -0.59
    ſelves
    -0.59
    POSITIVE LOGITS
     includes
    0.52
     include
    0.50
     betrekking
    0.42
     incluyen
    0.42
     consisted
    0.41
    includes
    0.41
     largely
    0.40
     revolve
    0.40
     primarily
    0.39
     revolves
    0.39
    Activations Density 0.120%

    No Known Activations