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. 420
    Prev
    Next
    INDEX
    Explanations

    specific actions or processes related to food preparation or cooking

    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
     actionPerformed
    -0.39
    GeneratedCode
    -0.36
    ```
    -0.34
    ™
    -0.34
    Ingo
    -0.33
     Limburg
    -0.33
    StrictMode
    -0.32
    Примечания
    -0.32
     становника
    -0.32
     AssemblyCulture
    -0.32
    POSITIVE LOGITS
    endphp
    0.53
     vectorielle
    0.53
     therefore
    0.53
     auroit
    0.51
     duquel
    0.50
    majánló
    0.49
     leaſt
    0.49
     uș
    0.49
     apapun
    0.49
    @[+][
    0.48
    Activations Density 1.228%

    No Known Activations