© 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. 18-GEMMASCOPE-RES-16K
    11. 1882
    Prev
    Next
    INDEX
    Explanations

    scientific terms and phrases related to statistical analysis and experimental procedures

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

    Statistical test names

    np_acts-logits-general · gemini-2.0-flash

    statistical tests and DNA primers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    [toxicity=0]
    -0.75
     alike
    -0.71
     فريبيس
    -0.69
    ™.
    -0.68
    enumi
    -0.67
    ®.
    -0.63
    .
    -0.60
    })();
    -0.58
    ...:
    -0.57
    endphp
    -0.56
    POSITIVE LOGITS
    webElementXpaths
    0.73
    SourceChecksum
    0.70
    :✨
    0.69
     ModelExpression
    0.65
     ISNI
    0.63
    TagMode
    0.62
     ***!
    0.61
     ProtoMessage
    0.60
    зулта
    0.58
     CWE
    0.58
    Activations Density 1.155%

    No Known Activations