© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4234
    Prev
    Next
    INDEX
    Explanations

    instances of medical terminology and concepts related to health conditions

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

    mathematical or statistical terminology, particularly related to discrete or continuous observations, statistical models, and mathematical symbols.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    DebuggerNonUser
    -0.52
     consultato
    -0.49
    msgTypes
    -0.48
    ăsp
    -0.46
    nodoc
    -0.46
     ujedno
    -0.45
    <?
    -0.44
     semuanya
    -0.44
     endforeach
    -0.44
    ostante
    -0.43
    POSITIVE LOGITS
     or
    0.63
     oder
    0.62
     또는
    0.59
     alebo
    0.57
     või
    0.56
     eller
    0.54
     или
    0.54
     hoặc
    0.54
    หรือ
    0.54
     либо
    0.53
    Activations Density 0.476%

    No Known Activations