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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7866
    Prev
    Next
    INDEX
    Explanations

    cultural and identity-related expressions, particularly in the context of traditional clothing and societal contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exception
    -0.33
     Gud
    -0.32
     Erişim
    -0.32
    硬
    -0.31
     real
    -0.31
     hard
    -0.31
     Thur
    -0.30
     hår
    -0.30
     déposer
    -0.30
     DROP
    -0.29
    POSITIVE LOGITS
     وتسجيلات
    0.69
    addCriterion
    0.65
     ModelExpression
    0.64
    MessageTagHelper
    0.64
    
    0.64
    GEBURTSDATUM
    0.63
     disambiguazione
    0.62
    exitRule
    0.61
    enumii
    0.60
    WithIOException
    0.57
    Activations Density 1.729%

    No Known Activations