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 - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10372
    Prev
    Next
    INDEX
    Explanations

    references to specific athletes and their performance statistics

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

    Referring to someone who scored or finished with a statistic

    np_acts-logits-general · gemini-2.0-flash

    led, scored, averaged, finished

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hentet
    -0.58
    ngdoc
    -0.58
     xlink
    -0.57
    MessageOf
    -0.55
    jaros
    -0.55
    levance
    -0.54
    arai
    -0.54
     Kib
    -0.53
    rement
    -0.53
     couverture
    -0.52
    POSITIVE LOGITS
     averaged
    0.75
     finished
    0.74
     racked
    0.70
     Finished
    0.68
     tallied
    0.67
     led
    0.66
     averaging
    0.66
     ranks
    0.65
     notched
    0.65
     leads
    0.64
    Activations Density 0.212%

    No Known Activations