© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10443
    Prev
    Next
    INDEX
    Explanations

    elements related to coding problems and their solutions

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

    Code or code-related keywords

    np_acts-logits-general · gemini-2.0-flash

    function declarations

    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
     فريبيس
    -0.57
     linkovi
    -0.56
    LLocation
    -0.56
    GIVEREF
    -0.49
     Wikimedijinoj
    -0.48
    styleType
    -0.46
    __(/*!
    -0.45
     fört
    -0.44
     урна
    -0.44
    columnHeader
    -0.43
    POSITIVE LOGITS
    ViewImports
    0.52
    ########.
    0.51
     uLocal
    0.44
     method
    0.41
     Photocase
    0.41
    исленность
    0.41
    primaryColor
    0.38
    BitConverter
    0.38
    Demografie
    0.38
     inches
    0.36
    Activations Density 0.258%

    No Known Activations