Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 29516
    Prev
    Next
    INDEX
    Explanations

    instances of the word "spread" and its variations, often associated with the dissemination of information or ideas

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

    spread news, ideas, or things

    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
     surla
    -0.52
     فريبيس
    -0.48
    setupUi
    -0.47
     sitting
    -0.45
     Cabinet
    -0.44
     SIT
    -0.44
     duduk
    -0.43
     Appointments
    -0.43
    indd
    -0.42
    ագրություններ
    -0.42
    POSITIVE LOGITS
     Verbreitung
    0.79
     spreading
    0.79
     difusión
    0.79
     verbreitet
    0.76
     dissemination
    0.74
     propagation
    0.73
     verspre
    0.71
    spreading
    0.69
     spread
    0.68
     propagated
    0.67
    Activations Density 0.033%

    No Known Activations