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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 804
    Prev
    Next
    INDEX
    Explanations

    characteristic patterns in code and markup

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

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     imó
    -0.38
     paljon
    -0.37
     egna
    -0.35
    ModelMap
    -0.35
    ciaal
    -0.34
     consentement
    -0.34
     küpe
    -0.34
     Camargo
    -0.33
     charité
    -0.33
    RSpec
    -0.33
    POSITIVE LOGITS
     nakalista
    0.89
    :✨
    0.50
    providedIn
    0.45
     estekak
    0.45
     EconPapers
    0.44
    #
    0.43
     ویکی‌پدی
    0.42
    хьтан
    0.42
     thế
    0.41
    webElementXpaths
    0.41
    Activations Density 0.005%

    No Known Activations