© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 506
    Prev
    Next
    INDEX
    Explanations

    quantitative data or metrics related to performance

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

    tokens indicating negative results or errors in response handling

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

    radical solutions

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ↵
    -0.67
    <b>
    -0.58
    ​
    -0.53
     rembour
    -0.51
    ↵↵
    -0.50
    -0.49
    <eos>
    -0.48
    råd
    -0.48
    <strong>
    -0.47
    モール
    -0.46
    POSITIVE LOGITS
     }}$}
    1.12
    tvguidetime
    1.11
    __":

    1.00
     myſelf
    0.94
    __':

    0.93
    BibitemShut
    0.91
     Paglinawan
    0.91
    出版年
    0.88
    bibinfo
    0.88
    RenderAtEndOf
    0.86
    Activations Density 0.005%
    No Known Activations