© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15146
    Prev
    Next
    INDEX
    Explanations

    technical terminology and descriptions related to experiments and numerical results in scientific contexts

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

    Referring to figures (e.g., "Figure 1", "Fig. 2")

    np_acts-logits-general · gemini-2.0-flash

    is shown in figure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    BufferException
    -0.58
    ?
    -0.58
    Билгалдахарш
    -0.58
    VOA
    -0.56
    numerusform
    -0.55
    Tracce
    -0.52
    ագրություններ
    -0.50
    Viitteet
    -0.50
    writeFieldEnd
    -0.50
    出版年
    -0.50
    POSITIVE LOGITS
     Figure
    2.45
    Figure
    2.31
     Fig
    2.29
    Fig
    2.20
     figure
    1.88
    figure
    1.87
     Figura
    1.84
     FIGURE
    1.79
    FIGURE
    1.79
     Figs
    1.79
    Activations Density 1.975%

    No Known Activations