© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6337
    Prev
    Next
    INDEX
    Explanations

    terms related to recruitment and participant enrollment in studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     erfaring
    -0.42
    cię
    -0.41
     betale
    -0.40
     tarvit
    -0.39
    füh
    -0.37
    cityId
    -0.36
     Steen
    -0.36
    pageId
    -0.36
     AssemblyTitle
    -0.36
     ferdig
    -0.35
    POSITIVE LOGITS
     recruiting
    0.75
     baseline
    0.73
     Baseline
    0.69
     Recruiting
    0.69
     recruited
    0.69
     recruit
    0.68
    Baseline
    0.68
     recruitment
    0.67
    baseline
    0.65
     Recruitment
    0.65
    Activations Density 0.080%

    No Known Activations