Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 3140
    Prev
    Next
    INDEX
    Explanations

    phrases indicating agreements, provisions, and clauses related to contracts and negotiations

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

    followed by their past participle form

    np_acts-logits-general · gemini-2.0-flash

    inclusion or incorporation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     contextLoads
    -0.81
     myſelf
    -0.70
    SequentialGroup
    -0.69
    __":
    
    -0.67
     Shaksp
    -0.66
    +#+
    -0.62
     transfieras
    -0.61
    MemoryWarning
    -0.61
     anſ
    -0.61
     themſelves
    -0.60
    POSITIVE LOGITS
     inclusion
    2.29
     included
    2.18
     incorporated
    2.10
    included
    1.93
     Inclusion
    1.82
     incorporation
    1.82
     Included
    1.79
    Included
    1.77
    inclusion
    1.76
    Inclusion
    1.75
    Activations Density 0.779%

    No Known Activations