© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15876
    Prev
    Next
    INDEX
    Explanations

    references to measurements, specifications, and characteristics of objects

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

    Comes before a unit of measure

    np_acts-logits-general · gemini-2.0-flash

    raw, unmodified, or measured states

    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
    IUrlHelper
    -0.73
     '\\;'
    -0.66
    ()?;
    -0.63
     ISNI
    -0.57
    AutoresizingMask
    -0.56
    новништво
    -0.56
    reszcie
    -0.55
     jScrollPane
    -0.55
    Népesség
    -0.55
    tdessen
    -0.54
    POSITIVE LOGITS
     raw
    1.15
     un
    1.00
     naked
    0.96
     bare
    0.93
     uncut
    0.92
     unloaded
    0.92
     unmodified
    0.91
    raw
    0.90
     unpacked
    0.84
     untreated
    0.83
    Activations Density 0.607%

    No Known Activations