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. 10253
    Prev
    Next
    INDEX
    Explanations

    references to job offers and recruitment processes

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

    hiring, recruitment, and interviews

    np_acts-logits-general · gemini-2.0-flash

    hiring and interviews

    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
    UserScript
    -0.54
    ссора
    -0.53
     дописавши
    -0.51
    bena
    -0.50
     незавершена
    -0.50
     onlyOwner
    -0.47
    кипедия
    -0.46
     captivity
    -0.45
    UPI
    -0.45
    batore
    -0.45
    POSITIVE LOGITS
     hiring
    1.68
     recruiter
    1.65
     recruiters
    1.65
     interview
    1.58
     Hiring
    1.58
     recruitment
    1.58
     interviewing
    1.55
     interviewers
    1.50
     recruiting
    1.46
     interviews
    1.43
    Activations Density 0.310%

    No Known Activations