© 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. 24-GEMMASCOPE-RES-16K
    6. 13618
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to molecular biology and genetic analysis

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

    Text after section/list headings

    np_acts-logits-general · gemini-2.0-flash

    containing added, evidence presented

    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
     estekak
    -0.81
    aarrggbb
    -0.79
    abestanden
    -0.78
    DoubleQuotes
    -0.77
    AndEndTag
    -0.76
     <=",
    -0.76
    __*/
    -0.74
     EconPapers
    -0.73
    makeConstraints
    -0.73
    kháu
    -0.71
    POSITIVE LOGITS
    exels
    0.49
    Labels
    0.47
     labels
    0.47
     helft
    0.45
     Labels
    0.42
    Firstly
    0.41
    anmoins
    0.40
    Brands
    0.39
     continente
    0.38
     Continent
    0.38
    Activations Density 0.144%

    No Known Activations