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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-GEMMASCOPE-RES-16K
    6. 5123
    Prev
    Next
    INDEX
    Explanations

    references to construction and project management activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.50
    RetentionPolicy
    -0.50
     Xamarin
    -0.50
     endowed
    -0.49
     automat
    -0.47
     aparato
    -0.46
     automatiques
    -0.45
     Automat
    -0.45
     perpetuity
    -0.45
     saut
    -0.45
    POSITIVE LOGITS
     contractor
    1.01
     contractors
    0.96
     Contractors
    0.94
    contractor
    0.91
     construction
    0.88
     Contractor
    0.86
     chantier
    0.86
     Construction
    0.86
    Contractor
    0.85
     subcontra
    0.84
    Activations Density 0.275%

    No Known Activations