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. 18-GEMMASCOPE-RES-16K
    6. 1484
    Prev
    Next
    INDEX
    Explanations

    phrases indicating necessity or urgent requests

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

    followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    desired items and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ritz
    -0.46
     neu
    -0.44
    [])
    
    -0.43
    varna
    -0.43
     Berna
    -0.42
     insufficient
    -0.41
    令人
    -0.41
    Достоинства
    -0.41
    v
    -0.41
    try
    -0.41
    POSITIVE LOGITS
     urgently
    0.96
     estekak
    0.95
     urgente
    0.86
     desperately
    0.85
     oprot
    0.84
    TagMode
    0.83
     helst
    0.83
     Réponses
    0.82
     desesper
    0.82
     صوتيه
    0.81
    Activations Density 0.245%

    No Known Activations