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. 2084
    Prev
    Next
    INDEX
    Explanations

    phrases related to leadership and its influence

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

    Following "the"

    np_acts-logits-general · gemini-2.0-flash

    under supervision or control

    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
    antMatchers
    -0.46
    évaluateur
    -0.43
    ffre
    -0.43
     partea
    -0.42
     actualité
    -0.41
    stuffs
    -0.41
     trier
    -0.40
    avenir
    -0.38
     fieldNum
    -0.38
    ksikon
    -0.38
    POSITIVE LOGITS
     auspices
    1.36
     supervision
    1.31
     guidance
    1.23
     aegis
    1.19
    guidance
    1.11
     tute
    1.07
     umbrella
    1.00
     watchful
    0.99
     influence
    0.99
     patronage
    0.96
    Activations Density 0.242%

    No Known Activations