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. 3423
    Prev
    Next
    INDEX
    Explanations

    negative sentiments and criticisms toward people or concepts associated with social behavior and attitudes

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

    Preceding words of negative sentiment

    np_acts-logits-general · gemini-2.0-flash

    rude or negative behavior

    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
    
    -0.73
    AnimationsModule
    -0.63
    +:+
    -0.62
     sanity
    -0.61
    ⓧ
    -0.60
    ParallelGroup
    -0.58
    sanity
    -0.57
    culata
    -0.57
    sior
    -0.55
    RenderAtEndOf
    -0.54
    POSITIVE LOGITS
     rude
    1.10
     disrespectful
    1.03
     arrogant
    0.98
     selfish
    0.94
    rude
    0.91
     insensitive
    0.88
     rud
    0.87
     Rude
    0.84
     condescending
    0.84
     unfriendly
    0.83
    Activations Density 0.335%

    No Known Activations