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. 10-GEMMASCOPE-RES-16K
    6. 11739
    Prev
    Next
    INDEX
    Explanations

    references to specific items or concepts, typically emphasizing their significance or relevance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dopodob
    -0.72
    ROIT
    -0.68
     informaci
    -0.68
     Mard
    -0.63
     ddelweddau
    -0.62
     Dul
    -0.62
     roule
    -0.61
     Kleidung
    -0.61
     Gard
    -0.60
    nonumber
    -0.59
    POSITIVE LOGITS
    These
    1.36
     these
    1.30
     These
    1.23
     THESE
    1.17
    these
    1.15
     theses
    1.06
     Theses
    1.03
    这些
    1.02
    Эти
    0.98
    hese
    0.98
    Activations Density 0.124%

    No Known Activations