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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13-GEMMASCOPE-RES-16K
    6. 6748
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific prepositions and conjunctions in various languages, indicating focus on locative or comparative contexts

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

    occurrences of specific names and references to notable entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.90
     Bask
    -0.78
    unitOfWork
    -0.77
     Irvin
    -0.76
    переди
    -0.74
     Corm
    -0.74
     čierna
    -0.74
     GOB
    -0.74
    ..\..\
    -0.72
    oulder
    -0.71
    POSITIVE LOGITS
     на
    1.13
    Auf
    1.02
     auf
    0.98
     Auf
    0.91
    На
    0.88
     naf
    0.88
     Katsu
    0.87
     На
    0.86
     na
    0.83
    ENAME
    0.80
    Activations Density 0.172%

    No Known Activations