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. 20-GEMMASCOPE-RES-16K
    6. 7677
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and their performance or transactions

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

    Following team names or pronouns

    np_acts-logits-general · gemini-2.0-flash

    recruiting or hiring people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoScaleMode
    -0.79
     مشين
    -0.63
    GEBURTSDATUM
    -0.62
    verwijspagina
    -0.61
    Portail
    -0.58
    EndInit
    -0.58
     jsPsych
    -0.57
     StringTokenizer
    -0.57
    AddTagHelper
    -0.57
    Билгалдахарш
    -0.56
    POSITIVE LOGITS
     recruiting
    1.32
     hiring
    1.31
     recruit
    1.23
     recruited
    1.22
     hire
    1.13
     Hiring
    1.11
     appointing
    1.11
    Hiring
    1.07
     hires
    1.07
    Recruit
    1.06
    Activations Density 0.363%

    No Known Activations