© 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. 12221
    Prev
    Next
    INDEX
    Explanations

    specialized terms and identifiers in academic or technical contexts

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

    technical terminology in academic, scientific, and computing contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    yntaxException
    -0.85
    VersionUID
    -0.83
    OGND
    -0.79
    TargetException
    -0.78
    ruptedException
    -0.78
     تضيفلها
    -0.75
    脚注の使い方
    -0.72
    URLException
    -0.71
    ScopeManager
    -0.70
    ISupport
    -0.70
    POSITIVE LOGITS
     EnglishChoose
    0.36
    arrollo
    0.32
     fuff
    0.31
     “
    0.30
    ℚ
    0.30
    ='';
    0.30
     postal
    0.30
     BUT
    0.29
    bibfield
    0.29
    『
    0.28
    Activations Density 1.914%

    No Known Activations