© 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. 13540
    Prev
    Next
    INDEX
    Explanations

    specific mathematical or scientific notation and symbols

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

    special symbols and characters used in technical notation like brackets, parentheses, and mathematical symbols.

    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
    GraphicsUnit
    -0.87
    #+#
    -0.84
    󠁣
    -0.79
    Personendaten
    -0.74
     GenerationType
    -0.73
    AutoField
    -0.71
     AssemblyVersion
    -0.70
    PreferredItem
    -0.69
    ChildScrollView
    -0.68
    󠁴
    -0.68
    POSITIVE LOGITS
     Franks
    0.39
    RAI
    0.36
    MAH
    0.36
     Ibarra
    0.36
     continually
    0.35
    áciu
    0.35
     Valdés
    0.35
    artan
    0.35
    HHH
    0.35
     Mexique
    0.34
    Activations Density 1.967%

    No Known Activations