© 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. 14396
    Prev
    Next
    INDEX
    Explanations

    identifiers and variable declarations

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

    Code-related keywords or names

    np_acts-logits-general · gemini-2.0-flash

    test or code snippets

    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
     otomatig
    -0.74
     EconPapers
    -0.60
     Administrativna
    -0.58
     فريبيس
    -0.55
    MigrationBuilder
    -0.54
     Chwiliwch
    -0.54
    HasAnnotation
    -0.54
    ftagPool
    -0.53
    URLException
    -0.53
    SequentialGroup
    -0.52
    POSITIVE LOGITS
    endmodule
    0.37
    introduction
    0.36
     isabel
    0.36
    disclosure
    0.32
     Eles
    0.31
     konfer
    0.31
    funeral
    0.30
    }\]
    0.30
    forChild
    0.30
     FontWeight
    0.29
    Activations Density 0.859%

    No Known Activations