© 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. 8119
    Prev
    Next
    INDEX
    Explanations

    references to influential leaders and their recognition in rankings

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

    mentions of awards, rankings, and recognition lists (e.g., being named to influential or “Top/Best” lists by notable organizations or publications).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    rankings and recognition in lists (such as "Top 50", "Best of", "Most Influential"), particularly in contexts involving competitive rankings, awards, or ordinal positions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    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
    GTCX
    -0.59
     tør
    -0.49
    HtmlAttribute
    -0.46
    ㅐ
    -0.46
     observation
    -0.43
    Xna
    -0.43
     nonUne
    -0.43
    rizona
    -0.42
    UnusedPrivate
    -0.42
    jRadioButton
    -0.41
    POSITIVE LOGITS
     gepubliceerd
    0.49
     lists
    0.47
     rankings
    0.46
    lorette
    0.45
     ujednoznacz
    0.45
     ranked
    0.42
     transf
    0.39
    DockStyle
    0.37
    crans
    0.37
     Rankings
    0.37
    Activations Density 0.067%

    No Known Activations