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. 7441
    Prev
    Next
    INDEX
    Explanations

    references to the term "Black."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    EndContext
    -1.02
    =$?
    -0.89
    IsMutable
    -0.86
     оригіналу
    -0.84
     الحره
    -0.84
    NameInMap
    -0.81
     ujednoznacz
    -0.78
     rospy
    -0.77
     */;
    -0.77
     متعلقه
    -0.76
    POSITIVE LOGITS
    Black
    0.83
    BLACK
    0.81
     BLACK
    0.78
    black
    0.77
     Black
    0.77
     black
    0.69
     ブラック
    0.68
    Schwar
    0.66
     Schwar
    0.61
     чор
    0.61
    Activations Density 0.117%

    No Known Activations