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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 12942
    Prev
    Next
    INDEX
    Explanations

    social interactions and gestures

    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
     livré
    -0.47
     CBD
    -0.45
     voulons
    -0.45
     pensieri
    -0.45
     mend
    -0.45
     Teo
    -0.44
    embeds
    -0.44
    atisme
    -0.43
    rition
    -0.43
    ære
    -0.42
    POSITIVE LOGITS
    LookAnd
    1.08
     nodding
    0.90
     nod
    0.89
    WithIOException
    0.89
     nods
    0.86
    MessageTagHelper
    0.85
     shrug
    0.83
     nodded
    0.83
     wink
    0.81
     waving
    0.81
    Activations Density 0.223%

    No Known Activations