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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 22593
    Prev
    Next
    INDEX
    Explanations

    references to governmental cabinet positions and roles

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

    government cabinet members

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     remonte
    -0.47
    conductor
    -0.45
    happens
    -0.45
     useAppContext
    -0.44
    expandindo
    -0.44
     getRule
    -0.44
     يتيمه
    -0.44
    referenced
    -0.44
     unlucky
    -0.44
     guy
    -0.44
    POSITIVE LOGITS
     Cabinet
    1.77
    Cabinet
    1.60
     cabinet
    1.41
    cabinet
    1.23
     Cabinets
    1.03
     cabinets
    0.95
     gabinete
    0.87
     cabinetry
    0.73
    Cabin
    0.62
     CAB
    0.58
    Activations Density 0.003%

    No Known Activations