© 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. 8167
    Prev
    Next
    INDEX
    Explanations

    elements that contain or are related to user interface components and code structures

    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
     itſelf
    -1.17
     myſelf
    -1.10
     Monfieur
    -1.01
     pleaſure
    -0.99
     propOrder
    -0.98
     uſed
    -0.97
     faſt
    -0.96
     themſelves
    -0.95
     iſt
    -0.95
     ſta
    -0.94
    POSITIVE LOGITS
     gonna
    0.68
    n
    0.61
    z
    0.61
    <bos>
    0.59
    辰
    0.56
    de
    0.54
    而
    0.54
     d
    0.54
    e
    0.53
    f
    0.53
    Activations Density 0.011%

    No Known Activations