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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1233
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussions on fairness and equity in economic arrangements

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

    Following "to" or a verb

    np_acts-logits-general · gemini-2.0-flash

    negotiating offers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     courriel
    -0.36
    miec
    -0.32
    team
    -0.31
    间
    -0.31
     team
    -0.30
    ссора
    -0.29
     Angriff
    -0.29
     droog
    -0.28
    teams
    -0.28
     Mitter
    -0.28
    POSITIVE LOGITS
     ویکی‌پدی
    0.63
     utafitiHapana
    0.59
    تقاوى
    0.57
    évaluateur
    0.54
    cyklopedia
    0.53
     Biôgrafia
    0.53
     negotiating
    0.52
    ionario
    0.52
     negotiate
    0.52
    ंदीखरीदारी
    0.51
    Activations Density 0.283%

    No Known Activations