© 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. 6739
    Prev
    Next
    INDEX
    Explanations

    test assertions related to object properties and their expectations in a programming context

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

    `.toBe` calls in testing contexts

    np_acts-logits-general · gemini-2.0-flash

    expect assertionstoBe or toEqual

    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
    CodedInputStream
    -0.70
    DockStyle
    -0.68
     estimés
    -0.59
    BeginInit
    -0.57
    Autoritní
    -0.56
    帖最后由
    -0.54
     initComponents
    -0.54
    SEGU
    -0.54
    canton
    -0.53
    transQ
    -0.53
    POSITIVE LOGITS
    deep
    0.59
     cavallo
    0.56
    ok
    0.55
     deep
    0.54
    Deep
    0.53
    antry
    0.52
    eql
    0.51
     Deep
    0.51
    equal
    0.49
     provisoire
    0.48
    Activations Density 0.127%

    No Known Activations