© 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. 5373
    Prev
    Next
    INDEX
    Explanations

    textual references to legal terms and concepts related to historical context

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

    technical terminology and specific professional contexts (like Union history, programming code, scientific processes, or recipe instructions).

    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
    getOutput
    -0.32
     tương
    -0.32
     افت
    -0.31
     kald
    -0.31
     شهد
    -0.31
     Pa
    -0.30
     شر
    -0.30
     cả
    -0.30
    pantaloni
    -0.29
    lève
    -0.29
    POSITIVE LOGITS
     anymore
    0.87
    TagMode
    0.73
     אלא
    0.70
     المعيارى
    0.64
     melainkan
    0.64
     sondern
    0.64
    RTEX
    0.63
     للاسماء
    0.63
     necessarily
    0.62
    AsUp
    0.60
    Activations Density 0.944%

    No Known Activations