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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14902
    Prev
    Next
    INDEX
    Explanations

    terms and discussions related to disabilities and accessibility

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

    Terms related to disability

    np_acts-logits-general · gemini-2.0-flash

    disability, blindness, wheelchair

    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
    sizeCache
    -0.50
     financeiro
    -0.49
    تقاوى
    -0.48
     culturelle
    -0.48
     Paglinawan
    -0.48
     OMITBAD
    -0.47
    ]")]
    -0.47
     extérieures
    -0.45
     testigo
    -0.44
     toekomst
    -0.44
    POSITIVE LOGITS
     disabled
    1.14
     disability
    1.09
     Disability
    1.06
     Disabled
    1.03
     disabilities
    0.99
     wheelchair
    0.98
    Disability
    0.95
    Disabled
    0.91
     Disabilities
    0.90
     wheelchairs
    0.85
    Activations Density 0.206%

    No Known Activations