© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 3975
    Prev
    Next
    INDEX
    Explanations

    scientific notations related to genetics

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

    Capital letters followed by a period

    np_acts-logits-general · gemini-2.0-flash

    B.S., B.A., B.F.A. degrees

    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
    S
    -0.98
    T
    -0.79
    A
    -0.78
    M
    -0.78
    C
    -0.78
    E
    -0.77
    которые
    -0.76
    withstanding
    -0.76
    R
    -0.73
    i
    -0.71
    POSITIVE LOGITS
     AssemblyCulture
    0.60
     financières
    0.57
    IconModule
    0.57
     Савезне
    0.56
    ThemeOverlay
    0.56
    Hochspringen
    0.55
    ecutable
    0.54
    EndGlobalSection
    0.52
    antart
    0.51
    Durée
    0.51
    Activations Density 0.842%

    No Known Activations