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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53385
    Prev
    Next
    INDEX
    Explanations

    articles and descriptors that indicate the nature or quality of something

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

    positive words after articles

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    AsUp
    -0.71
    LookAnd
    -0.70
    Geplaatst
    -0.70
     '\\;'
    -0.70
    erview
    -0.69
    Билгалдахарш
    -0.68
     poffible
    -0.67
    Спољашње
    -0.66
     raiſ
    -0.66
    قایناقلار
    -0.66
    POSITIVE LOGITS
     excellent
    0.55
     fantastic
    0.54
     wonderful
    0.54
    celes
    0.53
     pretty
    0.49
     ótima
    0.49
     brilliant
    0.48
     well
    0.48
     remarkable
    0.48
     marvelous
    0.47
    Activations Density 0.075%

    No Known Activations