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. 0-GEMMASCOPE-RES-16K
    6. 6429
    Prev
    Next
    INDEX
    Explanations

    references to academic or career stages, particularly focusing on the terms "senior" and "freshman."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "
    -0.70
     “
    -0.68
      
    -0.67
     
    -0.65
     (
    -0.59
     A
    -0.56
     $
    -0.52
     I
    -0.52
    ↵↵
    -0.51
     p
    -0.51
    POSITIVE LOGITS
     poffible
    1.10
     myſelf
    1.07
     Monfieur
    1.07
     itſelf
    1.06
     againſt
    1.06
     Anſ
    1.04
     Jefus
    1.04
     Theſe
    1.03
     whoſe
    1.03
     Majefty
    1.02
    Activations Density 0.208%

    No Known Activations