© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 15006
    Prev
    Next
    INDEX
    Explanations

    complex scientific terminology and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orologio
    -0.40
    astify
    -0.37
    setTextSize
    -0.36
    IntoConstraints
    -0.35
     Zeng
    -0.35
    ApiRequest
    -0.34
     Zeits
    -0.34
     Zappa
    -0.33
    zoic
    -0.33
     sark
    -0.33
    POSITIVE LOGITS
    H
    1.03
     hydrogen
    1.03
     HH
    1.02
     HC
    1.01
     H
    1.01
     h
    0.95
     HD
    0.94
     HP
    0.93
    HC
    0.91
     himo
    0.91
    Activations Density 1.294%

    No Known Activations