© 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. 4954
    Prev
    Next
    INDEX
    Explanations

    conditional statements and branching structures in code

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

    Code containing "if" or "for" statements

    np_acts-logits-general · gemini-2.0-flash

    if (

    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
    ValueStyle
    -0.71
     bezeichneter
    -0.62
    ">
    -0.59
    ',
    -0.59
     Administrativna
    -0.55
     Audiodateien
    -0.55
    Autoritní
    -0.54
    ?—
    -0.52
    );
    -0.52
    gers
    -0.51
    POSITIVE LOGITS
    (
    0.94
    {
    0.76
    GenerationType
    0.75
    ((
    0.69
    [
    0.68
    (!
    0.66
    EndGlobalSection
    0.61
    {[
    0.58
    addCriterion
    0.57
    obacterium
    0.55
    Activations Density 0.052%

    No Known Activations