© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 3260
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating manner of action or quality

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    ending in "-ly" followed by a preposition or conjunction

    np_acts-logits-general · gemini-2.0-flash

    manner adverbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    RenderAtEndOf
    -0.69
    "},
    -0.57
    >";
    -0.57
    '].'
    -0.56
     *>(
    -0.55
    ']?>
    -0.55
    ":{"
    -0.55
    >';
    -0.54
     ")
    -0.54
    (")
    -0.54
    POSITIVE LOGITS
     רבה
    0.91
    enough
    0.76
     enough
    0.75
    altri
    0.67
     ilman
    0.67
     متعلقه
    0.66
     zaidi
    0.65
     genoeg
    0.60
     ביותר
    0.59
     afield
    0.59
    Activations Density 0.387%

    No Known Activations