© 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. 16-GEMMASCOPE-RES-16K
    11. 16340
    Prev
    Next
    INDEX
    Explanations

    data relating to statistical estimation and analysis

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

    Tokens preceding bracketed numbers

    np_acts-logits-general · gemini-2.0-flash

    page ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Diſ
    -0.75
     Houſe
    -0.73
     Reſ
    -0.73
     Anſ
    -0.71
     Efq
    -0.67
    neſs
    -0.67
     Jefus
    -0.66
     Hift
    -0.64
     purpoſe
    -0.64
     pleaſure
    -0.63
    POSITIVE LOGITS
    ServletException
    0.60
    VolleyError
    0.58
     endwhile
    0.56
     TextAppearance
    0.55
     sacré
    0.53
    脚注の使い方
    0.51
     yoktur
    0.48
     extiende
    0.48
    참고
    0.48
    CrossRef
    0.47
    Activations Density 0.189%

    No Known Activations