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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11530
    Prev
    Next
    INDEX
    Explanations

    code structures and syntax elements related to programming and data manipulation

    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
    MLLoader
    -0.79
    CloseOperation
    -0.68
     صوتيه
    -0.67
    Бахар
    -0.64
    Xna
    -0.64
    andExpect
    -0.63
    FormTagHelper
    -0.61
     itſelf
    -0.59
     JpaRepository
    -0.59
    IsContent
    -0.59
    POSITIVE LOGITS
     Turquía
    0.36
    temp
    0.35
     defaultstate
    0.34
     monasterio
    0.32
     ins
    0.32
     Moskau
    0.31
     offending
    0.31
    pushd
    0.31
     Canadá
    0.31
    val
    0.31
    Activations Density 0.476%

    No Known Activations