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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5409
    Prev
    Next
    INDEX
    Explanations

    scientific measurements and units of measurement

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

    Units of measure: km, cm, erg

    np_acts-logits-general · gemini-2.0-flash

    units of length and energy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndContext
    -0.53
    #![
    -0.52
    ')")
    -0.49
    %");
    -0.49
    setw
    -0.48
    ogon
    -0.47
    "]);
    
    -0.47
     argv
    -0.46
    emit
    -0.46
    jfree
    -0.44
    POSITIVE LOGITS
    PerSecond
    0.73
    OGND
    0.66
    >{@
    0.62
    SequentialGroup
    0.62
     ddelweddau
    0.62
     Wallflower
    0.56
     per
    0.55
    principalColumn
    0.55
     dimensionless
    0.55
     hour
    0.53
    Activations Density 0.472%

    No Known Activations