© 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. 14894
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and sentence endings.

    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
    nextProps
    -0.56
     there
    -0.51
     nữa
    -0.50
    kuuta
    -0.48
    paramref
    -0.45
     évent
    -0.44
     есть
    -0.44
     depends
    -0.44
     occasional
    -0.43
    lietta
    -0.43
    POSITIVE LOGITS
     founded
    1.31
     designed
    1.24
     Created
    1.18
     Launched
    1.17
     Designed
    1.17
     Founded
    1.17
     born
    1.15
     Composed
    1.14
     conceived
    1.14
     formed
    1.13
    Activations Density 0.166%

    No Known Activations