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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 5292
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases associated with research and medical contexts, specifically those related to evaluation and treatment

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

    technical or scientific language related to research, analysis, and experimental processes.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    words that function as reference points or standards in technical and scientific contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.57
    tagHelperRunner
    -0.55
    новниш
    -0.54
     myſelf
    -0.52
    ſelf
    -0.51
    ViewImports
    -0.50
     linkovi
    -0.49
     InputDecoration
    -0.48
    SequentialGroup
    -0.48
     indígen
    -0.48
    POSITIVE LOGITS
     sebagai
    2.16
     as
    2.08
    作为
    1.89
    作為
    1.75
    sebagai
    1.66
    作为一个
    1.64
     Sebagai
    1.63
     ως
    1.63
     jako
    1.49
     به‌عنوان
    1.46
    Activations Density 2.528%

    No Known Activations