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. 1065
    Prev
    Next
    INDEX
    Explanations

    instances of the word "instead" and its variations, indicating a preference for alternatives or changes in perspective

    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
     "));
    -0.94
     
    -0.84
     GAO
    -0.79
     Schengen
    -0.79
    "));
    
    -0.78
    ."));
    -0.76
    ."),
    -0.76
     Rik
    -0.76
     SAE
    -0.76
     protoimpl
    -0.75
    POSITIVE LOGITS
     Instead
    1.23
    Instead
    1.19
     instead
    1.08
    instead
    0.96
    uttosto
    0.88
     Rather
    0.84
    Rather
    0.82
     Statt
    0.75
    katapos
    0.74
     rather
    0.73
    Activations Density 0.156%

    No Known Activations