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
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 15030
    Prev
    Next
    INDEX
    Explanations

    references to disabilities and their implications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Exacts
    -0.45
    PerformLayout
    -0.40
    хьтан
    -0.40
     '\\;'
    -0.40
    jsonwebtoken
    -0.39
     "]";
    -0.37
    Géographie
    -0.37
    pulumi
    -0.36
    Obfuscated
    -0.36
    IntoConstraints
    -0.34
    POSITIVE LOGITS
     disability
    2.19
     disabled
    2.06
     Disability
    1.91
     wheelchair
    1.84
     disabilities
    1.83
    Disability
    1.83
     Disabled
    1.82
     handicapped
    1.74
     handicap
    1.72
     disable
    1.66
    Activations Density 0.573%

    No Known Activations