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. 12-GEMMASCOPE-RES-16K
    6. 10187
    Prev
    Next
    INDEX
    Explanations

    references to specific subjects or topics in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.72
     osu
    -0.71
     lein
    -0.71
     Coff
    -0.71
     Agamemnon
    -0.70
     Phry
    -0.70
     Rosalie
    -0.69
    enderror
    -0.68
     Dubuque
    -0.68
    RectangleBorder
    -0.68
    POSITIVE LOGITS
     THIS
    1.49
     this
    1.46
    THIS
    1.39
    this
    1.27
    This
    1.25
     This
    1.24
     esta
    1.04
     este
    0.98
     بهذا
    0.96
     questa
    0.96
    Activations Density 0.357%

    No Known Activations