© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2936
    Prev
    Next
    INDEX
    Explanations

    references to structured data and programming concepts

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

    C code bitfields and math symbols

    np_acts-logits-general · gemini-2.0-flash

    technical identifiers, code, or non-English

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.51
    inSlope
    -0.49
    StoreMessageInfo
    -0.47
    gonic
    -0.47
     EconPapers
    -0.46
    politan
    -0.44
     Dummy
    -0.44
     TextInputType
    -0.43
    useState
    -0.43
    ignty
    -0.43
    POSITIVE LOGITS
    Välislingid
    0.49
    oredCriteria
    0.44
     مشين
    0.42
     Савезне
    0.41
     وتسجيلات
    0.41
     يتيمه
    0.40
    Hochspringen
    0.40
    Amicalement
    0.39
     незавершена
    0.38
    principalTable
    0.35
    Activations Density 1.121%

    No Known Activations