© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 2623
    Prev
    Next
    INDEX
    Explanations

    the word "even" in various contexts to assess emphasis or contrast in statements

    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
     even
    -0.80
     incluso
    -0.76
    甚至
    -0.71
     either
    -0.71
     даже
    -0.68
     bahkan
    -0.68
     nawet
    -0.66
     حتی
    -0.66
     thậm
    -0.63
    Either
    -0.62
    POSITIVE LOGITS
     though
    1.11
    though
    1.01
    handed
    0.80
    handedly
    0.77
    Though
    0.77
     THOUGH
    0.74
     worse
    0.70
     Though
    0.69
    emang
    0.57
    verständlich
    0.57
    Activations Density 0.104%

    No Known Activations