© 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. 20-GEMMASCOPE-RES-16K
    11. 14970
    Prev
    Next
    INDEX
    Explanations

    configuration parameters or settings in a structured format

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

    Follows a colon

    np_acts-logits-general · gemini-2.0-flash

    JSON structure delimiters

    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
     ‘
    -0.93
     obstante
    -0.78
     entanto
    -0.77
    帖最后由
    -0.71
    =’
    -0.71
    aglia
    -0.67
    (‘
    -0.66
    ='\
    -0.66
     AssemblyCulture
    -0.65
    ً
    -0.63
    POSITIVE LOGITS
    '"
    0.86
    ")
    0.78
    '",
    0.76
    '".
    0.76
    ",
    0.76
    __*/
    0.72
    ??"
    0.71
     "^
    0.70
    ":
    0.69
    "
    0.69
    Activations Density 0.110%

    No Known Activations