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. 15375
    Prev
    Next
    INDEX
    Explanations

    themes of relatability and connection to personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Monfieur
    -0.95
     purpoſe
    -0.82
     houſe
    -0.81
     myſelf
    -0.77
     himſelf
    -0.77
     ſever
    -0.75
     pleaſure
    -0.74
     themſelves
    -0.73
     Jefus
    -0.73
     Houſe
    -0.72
    POSITIVE LOGITS
     resonates
    0.67
     resonate
    0.66
     reson
    0.60
     relatable
    0.49
     appeal
    0.48
     intuitively
    0.48
     appeals
    0.47
     appealed
    0.46
    TagHelper
    0.46
    Datuak
    0.45
    Activations Density 0.187%

    No Known Activations