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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3347
    Prev
    Next
    INDEX
    Explanations

    keywords related to job requirements and qualifications

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

    Requirements or preferences in job descriptions

    np_acts-logits-general · gemini-2.0-flash

    job requirements and qualifications

    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
    
    -0.67
    cendental
    -0.64
    PostMapping
    -0.62
    Хьажоргаш
    -0.58
    EndContext
    -0.56
     nämlich
    -0.56
     nowhere
    -0.54
    ÍC
    -0.54
    inheritDoc
    -0.54
    numerusform
    -0.53
    POSITIVE LOGITS
     preferably
    1.07
     Preferably
    0.87
     ideally
    0.87
     willingness
    0.83
    preferably
    0.82
     candidates
    0.81
     Willing
    0.80
     candidate
    0.80
     préférence
    0.79
    Willing
    0.77
    Activations Density 0.195%

    No Known Activations