© 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. 11-GEMMASCOPE-RES-16K
    11. 12957
    Prev
    Next
    INDEX
    Explanations

    comparative terms indicating size or duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     T
    -0.76
     k
    -0.75
     Z
    -0.73
     Mat
    -0.71
     j
    -0.71
     High
    -0.70
     Al
    -0.69
     mit
    -0.68
     K
    -0.68
     p
    -0.67
    POSITIVE LOGITS
     myſelf
    1.65
     itſelf
    1.56
    ſelf
    1.48
     leſs
    1.48
    ſelves
    1.44
     himſelf
    1.43
     ་་
    1.37
     Anſ
    1.37
     Jefus
    1.37
     reaſon
    1.35
    Activations Density 0.151%

    No Known Activations