© 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 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. 7096
    Prev
    Next
    INDEX
    Explanations

    expressions related to variable assignments and returns in programming

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

    C# code syntax and operators

    np_acts-logits-general · gemini-2.0-flash

    programming code constructs

    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
    [{\
    -0.59
     ourselves
    -0.57
     {'
    -0.54
    *{\
    -0.53
     [`
    -0.51
     razu
    -0.50
    pushButton
    -0.49
     iff
    -0.48
     VIAF
    -0.47
    =['
    -0.47
    POSITIVE LOGITS
     Convert
    1.04
    Convert
    1.01
     new
    0.77
    string
    0.77
    typeof
    0.77
    $"
    0.76
    new
    0.76
    Enumerable
    0.76
    System
    0.75
     $"
    0.74
    Activations Density 0.050%

    No Known Activations