© 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. 22-GEMMASCOPE-RES-16K
    11. 9959
    Prev
    Next
    INDEX
    Explanations

    statistical data related to demographics or population characteristics

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

    Numbers followed by a percentage sign

    np_acts-logits-general · gemini-2.0-flash

    percentages and ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hozzáférés
    -0.63
    èdia
    -0.59
     ***!
    -0.57
    ArgsConstructor
    -0.56
    +#+#
    -0.55
     ratio
    -0.55
    elebr
    -0.52
     ratios
    -0.51
    Rhestr
    -0.51
    TSCA
    -0.51
    POSITIVE LOGITS
    RegressionTest
    0.75
    UnusedPrivate
    0.58
    exitRule
    0.57
     époux
    0.56
    potranspiration
    0.55
    UnsafeEnabled
    0.52
    windowFixed
    0.52
     neutre
    0.52
    Termine
    0.52
     innamor
    0.51
    Activations Density 0.263%

    No Known Activations