© 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. 20-GEMMASCOPE-RES-16K
    11. 12328
    Prev
    Next
    INDEX
    Explanations

    attributes and values in a data structure, particularly in a JSON format

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

    Code snippets with URLs or file paths

    np_acts-logits-general · gemini-2.0-flash

    code delimiters and subsequent values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    "):
    -0.52
    '):
    -0.49
     =",
    -0.46
    ><><
    -0.44
    责任编辑
    -0.42
    ẾT
    -0.42
     also
    -0.41
    $")
    -0.41
    ?");
    -0.41
    ?')
    -0.41
    POSITIVE LOGITS
     Roskov
    1.05
     nahilalakip
    0.97
     ddelweddau
    0.86
    fjspx
    0.73
     JpaRepository
    0.73
    ///</
    0.72
     NSCoder
    0.72
     correctes
    0.72
    SourceChecksum
    0.72
    MigrationBuilder
    0.72
    Activations Density 0.731%

    No Known Activations