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. 20-GEMMASCOPE-RES-16K
    6. 4111
    Prev
    Next
    INDEX
    Explanations

    references to the color brown or entities associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "brown" and its capitalization variations

    np_acts-logits-general · gemini-2.0-flash

    brown sugar or Brown Man

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     }?>
    -0.61
    Ciri
    -0.59
    MessageTagHelper
    -0.57
     NgModule
    -0.56
     חיצוניים
    -0.56
    +#+#
    -0.55
     CreateTagHelper
    -0.55
     Numerade
    -0.54
    IntentFilter
    -0.54
     Ellison
    -0.53
    POSITIVE LOGITS
     Browns
    0.89
    BROWN
    0.78
     Brown
    0.75
     BROWN
    0.73
    Brown
    0.69
     browns
    0.68
    Brow
    0.67
     brownies
    0.66
    lee
    0.64
     Tan
    0.60
    Activations Density 0.077%

    No Known Activations