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. 13-GEMMASCOPE-RES-16K
    6. 22
    Prev
    Next
    INDEX
    Explanations

    instances of the word "present" and its variations, indicating discussions around presentations or the act of presenting information

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

    the concept or act of presenting something.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LogFactory
    -0.83
    XtraEditors
    -0.81
    
    -0.81
     الوطنيه
    -0.78
     Laws
    -0.76
    ankle
    -0.75
     Khu
    -0.73
    ñoz
    -0.72
    +#+#
    -0.72
    anasia
    -0.72
    POSITIVE LOGITS
     presents
    1.33
     presentations
    1.32
     Presents
    1.30
     presentation
    1.30
     presented
    1.28
     presenting
    1.27
     Presentations
    1.17
     Presentation
    1.16
     Presenting
    1.15
     PRESENT
    1.13
    Activations Density 0.079%

    No Known Activations