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. 14357
    Prev
    Next
    INDEX
    Explanations

    expressions of emotions related to experiences

    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
    brane
    -0.53
    ||}
    -0.53
    kolwiek
    -0.51
     igualmente
    -0.51
    Guerra
    -0.50
    ?>">
    -0.49
    以外は
    -0.49
    {?>
    -0.48
    Autoritní
    -0.48
     dõi
    -0.48
    POSITIVE LOGITS
    StoryboardSegue
    0.78
    tanleria
    0.63
     WONDER
    0.63
    AddHtmlAttribute
    0.60
     BoxFit
    0.59
    исленность
    0.59
    Wonderful
    0.59
    providedIn
    0.58
    DockStyle
    0.55
    IntoConstraints
    0.54
    Activations Density 0.066%

    No Known Activations