© 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. 28-GEMMASCOPE-RES-16K
    11. 5331
    Prev
    Next
    INDEX
    Explanations

    actions related to verification and checking processes

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

    Verifying or validating something

    np_acts-logits-general · gemini-2.0-flash

    check and validate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     оригіналу
    -0.49
    ectoria
    -0.44
     recognised
    -0.38
    endregion
    -0.38
     considerazione
    -0.37
    ghijkl
    -0.36
    oplastic
    -0.35
     investigation
    -0.34
     unrecognized
    -0.34
     recognized
    -0.34
    POSITIVE LOGITS
     whether
    0.80
     compliance
    0.78
     correctness
    0.77
     validity
    0.77
     adequacy
    0.75
     apakah
    0.71
     compatibility
    0.71
    是否
    0.69
     viability
    0.69
     adherence
    0.67
    Activations Density 0.531%

    No Known Activations