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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5790
    Prev
    Next
    INDEX
    Explanations

    occurrences of opening braces in code

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

    Followed by, or is, "return"

    np_acts-logits-general · gemini-2.0-flash

    get swap or return

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.74
    Tikang
    -0.73
     alternatively
    -0.69
    Suara
    -0.68
    webElementGuid
    -0.68
    -------------</
    -0.67
     secondly
    -0.66
    homonymie
    -0.66
    出版年
    -0.65
    下载附件
    -0.65
    POSITIVE LOGITS
     return
    0.63
    return
    0.62
    if
    0.49
     returns
    0.46
     Returns
    0.43
     Waray
    0.43
    static
    0.42
     säkert
    0.41
    void
    0.40
    pstead
    0.40
    Activations Density 0.078%

    No Known Activations