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. 16-GEMMASCOPE-RES-16K
    6. 2930
    Prev
    Next
    INDEX
    Explanations

    expressions of recommendation and interest towards engaging with content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Interest," "like," and positive sentiment

    np_acts-logits-general · gemini-2.0-flash

    interest, enjoyment, or usefulness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thâu
    -0.54
    Хьажоргаш
    -0.49
    värr
    -0.49
     Example
    -0.48
     StatefulWidget
    -0.47
    RenderAtEndOf
    -0.47
     example
    -0.47
    addCriterion
    -0.46
    NameValuePair
    -0.45
     exemplo
    -0.43
    POSITIVE LOGITS
     interest
    0.93
    interest
    0.90
    Interest
    0.84
     Interest
    0.82
    interested
    0.79
     interested
    0.78
    INTEREST
    0.78
     INTEREST
    0.74
    useful
    0.72
    Worth
    0.70
    Activations Density 0.186%

    No Known Activations