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

    Neuronpedia

    APICircuit 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. 10811
    Prev
    Next
    INDEX
    Explanations

    phrases related to mechanisms and methods in scientific or technical contexts

    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
     रेटिंग
    -0.47
    lious
    -0.44
     presiding
    -0.44
    ônus
    -0.41
    ✭✭
    -0.41
     gossi
    -0.41
     nltk
    -0.40
    Wahl
    -0.40
     giggling
    -0.40
     ungrateful
    -0.40
    POSITIVE LOGITS
     method
    0.80
     méthode
    0.75
     direct
    0.72
     méthodes
    0.71
     Method
    0.70
    traditional
    0.69
     método
    0.68
     Direct
    0.68
    RenderAtEndOf
    0.68
     indirect
    0.67
    Activations Density 0.950%

    No Known Activations