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. 728
    Prev
    Next
    INDEX
    Explanations

    specific terms related to mechanical processes and equipment

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

    specific object or process followed by description

    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
    ніципалі
    -0.64
     AssemblyCulture
    -0.61
     للاسماء
    -0.60
     CreateTagHelper
    -0.59
    tvguidetime
    -0.58
    RenderAtEndOf
    -0.58
    XmlAccessType
    -0.57
    Демографія
    -0.56
     Waray
    -0.56
    EndGlobalSection
    -0.54
    POSITIVE LOGITS
     fundido
    0.50
    able
    0.48
    ings
    0.45
    ability
    0.43
    fär
    0.42
     uppdater
    0.41
     lanzar
    0.41
    Extend
    0.39
    ing
    0.38
    Купить
    0.38
    Activations Density 0.307%

    No Known Activations