Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9661
    Prev
    Next
    INDEX
    Explanations

    specific types of crafting materials and techniques

    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
    +:+
    -0.83
     EdgeInsets
    -0.76
     Waray
    -0.75
     ligiloj
    -0.70
    انيف
    -0.70
    LEncoder
    -0.67
    +#+#
    -0.66
     propOrder
    -0.66
    rungsseite
    -0.65
    waitKey
    -0.64
    POSITIVE LOGITS
     Stamp
    0.77
    Stamp
    0.74
     card
    0.73
     stamping
    0.72
     cards
    0.67
     Stamps
    0.64
     stamp
    0.64
     stamps
    0.62
     Card
    0.58
    stamp
    0.57
    Activations Density 0.099%

    No Known Activations