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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 15477
    Prev
    Next
    INDEX
    Explanations

    references to hyperlinks or links in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    hyperlinks or URL references in text.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    als
    -0.32
    elle
    -0.32
     außerord
    -0.30
     μη
    -0.29
     angene
    -0.29
     betrieb
    -0.29
    ENTLY
    -0.29
    pi
    -0.29
    OfWeek
    -0.29
     mo
    -0.28
    POSITIVE LOGITS
     Link
    0.83
    StoryboardSegue
    0.82
     Links
    0.76
    RenderAtEndOf
    0.72
     Linkage
    0.72
     LINK
    0.70
     kaarangay
    0.70
    AddTagHelper
    0.70
    MessageTagHelper
    0.69
     مرئيه
    0.68
    Activations Density 0.122%

    No Known Activations