© 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. 14702
    Prev
    Next
    INDEX
    Explanations

    sequences of numeric values and their manipulations in code

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

    Go, error, and code-related terms

    np_acts-logits-general · gemini-2.0-flash

    code and error handling

    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
    {{/
    -0.73
     NSCoder
    -0.72
    audiovisuel
    -0.72
    UnusedPrivate
    -0.68
    GEBURTS
    -0.65
    :][
    -0.63
    //};
    -0.63
     שוליים
    -0.63
    RetentionPolicy
    -0.61
    yntaxException
    -0.60
    POSITIVE LOGITS
    fmt
    0.59
    Loop
    0.48
     _,
    0.48
     επί
    0.46
    LOOP
    0.45
     Cause
    0.45
     gom
    0.44
     Reproduce
    0.44
    trab
    0.44
     sel
    0.44
    Activations Density 0.108%

    No Known Activations