© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4038
    Prev
    Next
    INDEX
    Explanations

    terms related to metrics and parameters in technology or data management

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

    like "maybe" that express uncertainty

    np_acts-logits-general · gemini-2.0-flash

    hypotheticals or suggestions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gewöhnlich
    -0.44
     recientemente
    -0.43
     irmã
    -0.39
     often
    -0.38
     zahlreichen
    -0.36
     anteriormente
    -0.36
     recently
    -0.36
     excès
    -0.35
     recentemente
    -0.35
     usually
    -0.35
    POSITIVE LOGITS
    TypedDataSet
    0.77
     maybe
    0.71
    MigrationBuilder
    0.63
     magari
    0.63
     disambiguazione
    0.63
     būtų
    0.62
     would
    0.61
    maybe
    0.60
     JpaRepository
    0.60
    ItemBackground
    0.60
    Activations Density 1.058%

    No Known Activations