© 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-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 9673
    Prev
    Next
    INDEX
    Explanations

    references to timeframes, particularly midpoints within months or years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elemField
    -0.47
     lệ
    -0.41
    验证码
    -0.40
    إنه
    -0.38
     AssemblyCulture
    -0.36
    Leistung
    -0.35
    machung
    -0.35
     MenuView
    -0.33
     Fuer
    -0.33
    liferay
    -0.32
    POSITIVE LOGITS
     mid
    0.78
     ویکی‌پدی
    0.68
    mid
    0.65
    Mid
    0.64
     Mid
    0.63
    PYX
    0.57
     MID
    0.55
    sizeCache
    0.55
     midt
    0.54
    MID
    0.53
    Activations Density 0.083%

    No Known Activations