© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 2938
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals involved in research or academic contributions

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

    references to academic or professional affiliations and contributors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.79
     الرياضيه
    -0.74
    Xna
    -0.69
     Wikimedijinoj
    -0.67
    Décès
    -0.66
     ویکی‌پدی
    -0.64
    astify
    -0.59
     keting
    -0.58
    Diweddarwch
    -0.54
    Cyfarwyddwr
    -0.53
    POSITIVE LOGITS
     propOrder
    0.57
    তথ্যসূত্র
    0.55
     Avi
    0.53
    localctx
    0.52
     Yor
    0.51
    ExecuteReader
    0.50
     Ary
    0.50
     Pn
    0.49
     Riv
    0.49
     Mena
    0.49
    Activations Density 0.260%

    No Known Activations