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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 4416
    Prev
    Next
    INDEX
    Explanations

    references to Native American culture and contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.48
     arse
    -0.43
     envisaged
    -0.42
    cognised
    -0.42
    twimg
    -0.41
    providedIn
    -0.40
     ostavi
    -0.38
    xec
    -0.38
     hence
    -0.37
     ReSharper
    -0.37
    POSITIVE LOGITS
     vocabulary
    0.57
     Vocabulary
    0.56
    Vocabulary
    0.55
     Venn
    0.55
     Inquiry
    0.55
    Vocab
    0.54
    Inquiry
    0.52
     compare
    0.52
     vocab
    0.52
    Compare
    0.50
    Activations Density 0.263%

    No Known Activations