© 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. 14800
    Prev
    Next
    INDEX
    Explanations

    parentheses and the surrounding context, indicating a focus on technical or scientific notation

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

    abbreviations in parentheses, particularly scientific and technical acronyms.

    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
    AlterField
    -0.35
     cause
    -0.35
     acc
    -0.34
     otr
    -0.34
     must
    -0.33
     ran
    -0.33
     subs
    -0.32
     demands
    -0.32
     load
    -0.32
     leave
    -0.32
    POSITIVE LOGITS
    ="@+
    0.71
     kasarigan
    0.69
    ьаж
    0.62
    Datuak
    0.56
    rungsseite
    0.54
    ########.
    0.52
     Paglinawan
    0.52
    简称
    0.51
     $_(
    0.51
    chestra
    0.51
    Activations Density 0.197%

    No Known Activations