© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8816
    Prev
    Next
    INDEX
    Explanations

    specific programming-related terms and functions

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

    Unusual characters: _, -, $, UTF-8

    np_acts-logits-general · gemini-2.0-flash

    film review; MRSA; Virginia; matrix

    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
     SEDS
    -0.71
    //
    -0.68
     "..\..\..\
    -0.67
    kwds
    -0.61
     AssemblyCompany
    -0.61
    }/${
    -0.61
     Wikispecies
    -0.57
    ✨:
    -0.57
    ografija
    -0.56
    mael
    -0.56
    POSITIVE LOGITS
    -
    1.32
    _
    1.18
    ‐
    0.64
     ​​
    0.61
    ‑
    0.61
     وتسجيلات
    0.57
    Lähteet
    0.53
     فريبيس
    0.51
    <bos>
    0.50
    bufio
    0.48
    Activations Density 0.485%

    No Known Activations