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. 10450
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to divorce proceedings

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

    Legal terms related to divorce or separation

    np_acts-logits-general · gemini-2.0-flash

    legal proceedings for divorce

    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
    tagHelperRunner
    -0.82
    providedIn
    -0.75
     eventdata
    -0.73
    IsContent
    -0.67
     inward
    -0.64
     snippetHide
    -0.64
     الرياضيه
    -0.60
    endaftaran
    -0.59
    ToTensor
    -0.59
    AutoScaleMode
    -0.58
    POSITIVE LOGITS
     divorce
    1.32
     Divorce
    1.15
     divor
    1.10
    Divorce
    1.04
     divorced
    1.03
    div
    1.01
     separation
    0.93
     custody
    0.92
     Div
    0.87
     alimony
    0.86
    Activations Density 0.354%

    No Known Activations