Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 10895
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to divorce proceedings

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

    Follows articles (a, s, is, the, The) and precedes legal terms

    np_acts-logits-general · gemini-2.0-flash

    legal complaint and verdict

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     associées
    -0.66
     للاسماء
    -0.65
    stdc
    -0.63
     déploy
    -0.60
     heav
    -0.55
    بش
    -0.55
     sauvages
    -0.55
    likely
    -0.54
     encor
    -0.54
     overseen
    -0.54
    POSITIVE LOGITS
     defendant
    0.63
     appellant
    0.62
     paroi
    0.62
    Personensuche
    0.60
    weixin
    0.58
     complained
    0.57
    newswire
    0.53
     respondent
    0.53
     complain
    0.53
     plaintiff
    0.52
    Activations Density 3.943%

    No Known Activations