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. 5-GEMMASCOPE-RES-16K
    6. 16185
    Prev
    Next
    INDEX
    Explanations

    typesetting commands typically used in mathematical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sharma
    -0.68
     present
    -0.63
    Sharma
    -0.58
    Weblinks
    -0.57
     “
    -0.54
     pre
    -0.54
     pegged
    -0.54
    Que
    -0.52
    황
    -0.52
     isSet
    -0.52
    POSITIVE LOGITS
     \\
    1.54
     \\\
    1.22
    ;\\
    1.13
     :\\
    1.07
    }\\
    1.06
    hdashline
    1.06
    :\\
    1.06
     purpoſe
    1.05
    \}\\
    1.04
    ,\\
    1.04
    Activations Density 0.111%

    No Known Activations