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. 250
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific experiments and methodologies

    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
     duele
    -0.80
     kasarigan
    -0.77
    rrggbb
    -0.71
     étoit
    -0.70
     étoient
    -0.70
     muere
    -0.69
     immobilier
    -0.68
     anún
    -0.67
     girdle
    -0.67
    ContextHolder
    -0.67
    POSITIVE LOGITS
     Experiment
    1.00
     experiment
    0.96
     experiments
    0.96
     Experiments
    0.95
    Experiment
    0.93
     experimental
    0.90
     Experimental
    0.83
     EXPERIMENT
    0.81
     experimentally
    0.81
    Experiments
    0.80
    Activations Density 0.145%

    No Known Activations