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. 2-GEMMASCOPE-RES-16K
    6. 6208
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'willing'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.70
     للمعارف
    -0.70
    enderror
    -0.69
    flashdata
    -0.68
    <?,
    -0.67
     nemici
    -0.67
    aday
    -0.65
    Попис
    -0.65
     ricorda
    -0.65
    mujer
    -0.64
    POSITIVE LOGITS
     willing
    3.23
    willing
    2.70
     Willing
    2.44
    Willing
    2.35
     willingness
    2.18
     unwilling
    1.92
     willingly
    1.70
    願意
    1.42
    愿意
    1.35
     unwillingness
    1.25
    Activations Density 0.054%

    No Known Activations