© 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. 1793
    Prev
    Next
    INDEX
    Explanations

    terms associated with standards and norms

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

    words related to technical or industrial domains, such as machines, methods, and standard procedures.

    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
     initComponents
    -0.59
     juist
    -0.50
    Tikang
    -0.49
    الإنجليزية
    -0.47
    ongevity
    -0.47
    occupe
    -0.47
     eksklu
    -0.46
    iocene
    -0.46
     ausdrücklich
    -0.45
    PhysRevLett
    -0.45
    POSITIVE LOGITS
     ordinary
    1.22
     normal
    1.20
     обы
    1.12
    ordinary
    1.05
     Normal
    1.04
    Ordinary
    1.03
     standard
    1.03
    Normal
    1.02
    normal
    1.02
     Ordinary
    1.01
    Activations Density 0.390%

    No Known Activations