© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10930
    Prev
    Next
    INDEX
    Explanations

    code-related instructions and function definitions

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

    Code related to output or printing

    np_acts-logits-general · gemini-2.0-flash

    return or print code results

    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
     zieht
    -0.45
    śni
    -0.42
     cocked
    -0.42
     equalled
    -0.41
    UALA
    -0.41
     tienden
    -0.40
    geral
    -0.40
    clonal
    -0.39
    marle
    -0.39
     ATTR
    -0.39
    POSITIVE LOGITS
     print
    0.79
     Print
    0.74
     output
    0.72
     Output
    0.72
     betweenstory
    0.71
     OUTPUT
    0.70
     outputs
    0.70
     출력
    0.70
     Prints
    0.69
     Your
    0.69
    Activations Density 0.925%

    No Known Activations