© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13442
    Prev
    Next
    INDEX
    Explanations

    numerical values and formatting within a technical or programming context

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

    Code snippets or file paths

    np_acts-logits-general · gemini-2.0-flash

    log markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     capital
    -0.35
     ComVisible
    -0.32
    }}^
    -0.32
    _));
    -0.30
     setuptools
    -0.30
    ()}>
    -0.29
     conserv
    -0.29
    Capital
    -0.29
     apos
    -0.29
    rovnik
    -0.29
    POSITIVE LOGITS
    出版年
    0.90
    ########.
    0.84
    Personensuche
    0.82
    +#+
    0.78
    #+#
    0.71
    tvguidetime
    0.69
     שוליים
    0.67
     Paglinawan
    0.66
    Tikang
    0.66
    Datuak
    0.63
    Activations Density 0.021%

    No Known Activations