© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 13232
    Prev
    Next
    INDEX
    Explanations

    numeric patterns, specifically focusing on "x" followed by digits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jefus
    -1.13
     pleaſure
    -1.12
     ſmall
    -1.04
     poffible
    -1.04
     itſelf
    -1.02
     ſever
    -1.00
     greateſt
    -0.99
     houſe
    -0.97
     myſelf
    -0.96
     ſche
    -0.95
    POSITIVE LOGITS
    Sprintf
    0.50
    ,:);
    0.50
    ;",
    0.47
    Eigen
    0.46
     co
    0.46
    x
    0.45
    ",
    0.44
    <eos>
    0.44
     Co
    0.44
    textbackslash
    0.43
    Activations Density 0.071%

    No Known Activations