© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6640
    Prev
    Next
    INDEX
    Explanations

    various forms of the number "2" and references to web addresses or online platforms

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

    Numbers inside dates or versions

    np_acts-logits-general · gemini-2.0-flash

    numbers and dates

    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
     disambiguazione
    -1.13
    CppMethod
    -0.87
    MigrationBuilder
    -0.85
    parsedMessage
    -0.83
    Хьажоргаш
    -0.82
    
    -0.81
     فريبيس
    -0.78
    PhysRev
    -0.77
    bootstrapcdn
    -0.76
    tagHelperRunner
    -0.74
    POSITIVE LOGITS
     sto
    0.28
    älä
    0.28
     Beek
    0.25
    Doc
    0.25
    Sto
    0.25
     dentaire
    0.25
    <eos>
    0.25
    Squared
    0.24
    Main
    0.24
     comune
    0.23
    Activations Density 0.117%

    No Known Activations