Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3581
    Prev
    Next
    INDEX
    Explanations

    references to individuals or entities, particularly those starting with "Ste."

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

    "Ste" at the beginning of words

    np_acts-logits-general · gemini-2.0-flash

    Ste- prefixed words

    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
    httphttps
    -0.71
    mergeFrom
    -0.68
    rawtypes
    -0.66
     disambiguazione
    -0.66
     Jennings
    -0.63
    脚注の使い方
    -0.61
    DialogContent
    -0.59
     Paglinawan
    -0.59
    **/
    
    -0.58
    Архівовано
    -0.58
    POSITIVE LOGITS
     Ste
    0.93
    Ste
    0.88
     ste
    0.81
     STE
    0.77
    ValueStyle
    0.65
    ste
    0.62
    STE
    0.61
     Stel
    0.58
     Stepan
    0.57
     Steer
    0.56
    Activations Density 0.074%

    No Known Activations