© 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. 24-GEMMASCOPE-RES-16K
    11. 9040
    Prev
    Next
    INDEX
    Explanations

    references to mathematical and computational frameworks, particularly in relation to testing and transformation functions

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

    ending in "Impl", "Test", or "View"

    np_acts-logits-general · gemini-2.0-flash

    common programming classes and tests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    ValueOf
    -0.57
    ReferenceEquals
    -0.55
    ValueStyle
    -0.52
    featureID
    -0.50
    ंदीखरीदारी
    -0.50
    igur
    -0.48
    setof
    -0.47
    suz
    -0.47
    DataURL
    -0.45
     ...]
    -0.45
    POSITIVE LOGITS
    IntoConstraints
    0.66
    Impl
    0.64
     extended
    0.60
     extends
    0.56
     externi
    0.56
     Extended
    0.56
    ⓧ
    0.56
    atiker
    0.54
     saurait
    0.54
     lenker
    0.54
    Activations Density 0.339%

    No Known Activations