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. 11562
    Prev
    Next
    INDEX
    Explanations

    specifications and instances of data formats

    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
     vicenda
    -0.47
    expandindo
    -0.47
    clientY
    -0.41
     OkHttpClient
    -0.41
     chì
    -0.41
    nonzero
    -0.40
    XmlNode
    -0.39
    encre
    -0.38
     subscriber
    -0.38
    Whis
    -0.38
    POSITIVE LOGITS
     Format
    1.27
    Format
    1.20
     format
    1.19
    format
    1.17
     FORMAT
    1.12
     Formats
    1.11
     formats
    1.03
    FORMAT
    0.93
    格式
    0.90
     格式
    0.88
    Activations Density 0.074%

    No Known Activations