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. 5-GEMMASCOPE-RES-16K
    6. 10171
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "black" or "Black" in various contexts within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -1.18
    VIAF
    -1.04
    __":
    
    -1.03
    MessageTagHelper
    -1.00
    RenderAtEndOf
    -0.98
    =$?
    -0.92
     оригіналу
    -0.92
    __':
    
    -0.91
    __":
    -0.90
    קישורים
    -0.89
    POSITIVE LOGITS
     Black
    2.12
    Black
    2.10
    black
    2.00
     black
    1.97
     BLACK
    1.95
    BLACK
    1.86
     blacks
    1.46
    黑
    1.43
     Blacks
    1.39
     Blackwell
    1.35
    Activations Density 0.050%

    No Known Activations