© 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. 12180
    Prev
    Next
    INDEX
    Explanations

    scientific measurements and diagnostic criteria

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

    Inequality comparisons

    np_acts-logits-general · gemini-2.0-flash

    quantities above or below threshold

    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
     ProtoMessage
    -0.70
    fjspx
    -0.68
    protoimpl
    -0.66
    AutoScaleMode
    -0.60
     disponibilités
    -0.60
    WebVitals
    -0.59
    InitVars
    -0.57
     فريبيس
    -0.57
    sizeCache
    -0.55
    SharedCtor
    -0.55
    POSITIVE LOGITS
     less
    1.80
     greater
    1.72
     exceeding
    1.65
     below
    1.60
     above
    1.57
    greater
    1.49
     ≥
    1.46
     >
    1.45
    above
    1.44
     $>
    1.44
    Activations Density 1.382%

    No Known Activations