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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 522
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and functions related to physics or mathematical theory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SizeF
    -0.70
     frequency
    -0.62
     frequencies
    -0.60
     parameter
    -0.55
     propOrder
    -0.53
    근
    -0.52
    hasMoreElements
    -0.51
    Bioaccumulative
    -0.51
     Frequencies
    -0.51
    پار
    -0.51
    POSITIVE LOGITS
     مرئيه
    0.78
    RenderAtEndOf
    0.68
    UserScript
    0.68
    Rüyada
    0.62
     متعلقه
    0.60
    ponses
    0.59
     Baillargeon
    0.55
     Audiodateien
    0.55
    UnsafeEnabled
    0.54
     ĝ
    0.52
    Activations Density 1.978%

    No Known Activations