© 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. 14653
    Prev
    Next
    INDEX
    Explanations

    specific programming structures and elements related to layouts and data handling in software

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

    Followed by articles or prepositions

    np_acts-logits-general · gemini-2.0-flash

    logarithmic scale or FIG

    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
     unknownFields
    -0.63
    EndGlobalSection
    -0.60
    providedIn
    -0.58
    SourceChecksum
    -0.55
     propOrder
    -0.54
    addGroup
    -0.52
    новниш
    -0.50
     дописавши
    -0.50
    aarrggbb
    -0.49
     nî
    -0.47
    POSITIVE LOGITS
    PREFERRED
    0.98
    Alignment
    0.83
    LayoutStyle
    0.80
    >--}}
    0.63
    DEFAULT
    0.63
     style
    0.61
     Audiodateien
    0.59
    **/
    0.59
     Style
    0.59
    yled
    0.58
    Activations Density 0.069%

    No Known Activations