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. 9-GEMMASCOPE-RES-16K
    6. 3901
    Prev
    Next
    INDEX
    Explanations

    terms related to labor disputes and legal actions

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

    preceding verbs like "said," "is," or "denied."

    np_acts-logits-general · gemini-2.0-flash

    reportedly said

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.71
    
    -0.70
     defaultstate
    -0.67
    ronpa
    -0.57
    ReusableCell
    -0.56
    awtextra
    -0.55
     noDo
    -0.55
    ConstraintMaker
    -0.54
    ArgsConstructor
    -0.54
    ContentLoaded
    -0.50
    POSITIVE LOGITS
     largely
    0.44
     prompted
    0.42
     led
    0.40
    xtext
    0.39
     sought
    0.39
     ivelany
    0.38
     reportedly
    0.38
     previously
    0.37
     widely
    0.37
     closely
    0.37
    Activations Density 0.593%

    No Known Activations