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 - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16065
    Prev
    Next
    INDEX
    Explanations

    numerical values and their associated mathematical relationships

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

    Numbers or math symbols preceded by hyphens or parenthesis

    np_acts-logits-general · gemini-2.0-flash

    negative numbers and operators

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Савезне
    -0.42
    неопр
    -0.34
     PagesJaunes
    -0.33
     pil
    -0.31
    Géographie
    -0.30
     littérature
    -0.30
     TOTAL
    -0.30
    Dens
    -0.29
    Примі
    -0.29
     proven
    -0.29
    POSITIVE LOGITS
     negative
    1.20
     (-
    1.17
     négatif
    1.05
     Negative
    1.02
    Negative
    1.02
    negative
    1.02
     [-
    1.02
    (-
    1.02
     $(-
    1.00
     negativ
    0.98
    Activations Density 1.839%

    No Known Activations