© 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. 12313
    Prev
    Next
    INDEX
    Explanations

    sentences that discuss the complexity or structure of sentences, particularly regarding their length and grammatical elements

    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
     pleaſure
    -0.94
     myſelf
    -0.91
     uſed
    -0.89
    setVerticalGroup
    -0.88
     himſelf
    -0.87
    ſelf
    -0.86
     themſelves
    -0.86
     purpoſe
    -0.85
     houſe
    -0.83
     Jefus
    -0.83
    POSITIVE LOGITS
    …
    0.61
     nice
    0.60
    ...
    0.59
     ça
    0.58
     b
    0.57
     :)
    0.57
    ....
    0.56
     w
    0.55
     shit
    0.55
     cool
    0.54
    Activations Density 0.027%

    No Known Activations