© 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. 996
    Prev
    Next
    INDEX
    Explanations

    occurrences of formatting tags in text, specifically bold and italic styles

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

    HTML tags (bold, italic) and LaTeX

    np_acts-logits-general · gemini-2.0-flash

    HTML tags and code comments

    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
    </em>
    -1.30
    </strong>
    -1.28
     fl
    -1.16
    fl
    -1.10
    <em>
    -0.96
    ",@"
    -0.94
    """
    -0.92
     first
    -0.90
     
    -0.89
     """
    -0.88
    POSITIVE LOGITS
    </b>
    2.31
    </i>
    2.09
    <i>
    1.58
    <b>
    1.50
    dfrac
    1.17
    ']").
    0.90
    </td>
    0.89
    '>
    0.88
     + 
    0.83
    َّ
    0.83
    Activations Density 0.242%

    No Known Activations