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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 85505
    Prev
    Next
    INDEX
    Explanations

    specific terms that pertain to cause-and-effect relationships or conditions

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

    prepositions and conjunctions

    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
     nämlich
    -0.36
    Gambas
    -0.32
    平
    -0.31
    TheReal
    -0.30
     ErrIntOverflow
    -0.28
     hin
    -0.28
     detailsLots
    -0.27
    fil
    -0.27
    multer
    -0.26
     المن
    -0.26
    POSITIVE LOGITS
     שוליים
    0.90
    RenderAtEndOf
    0.78
    Personensuche
    0.76
    PreferredItem
    0.72
    WithIOException
    0.69
     '{@
    0.66
    CloseOperation
    0.66
     initComponents
    0.65
     فريبيس
    0.65
    AddTagHelper
    0.64
    Activations Density 0.218%

    No Known Activations