© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9546
    Prev
    Next
    INDEX
    Explanations

    instances of rhetorical questions or memorable statements

    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
    curo
    -0.51
     toán
    -0.47
     vare
    -0.47
     photographs
    -0.46
    fn
    -0.46
     photograph
    -0.45
    Dims
    -0.44
     resim
    -0.44
    LError
    -0.44
    Photograph
    -0.44
    POSITIVE LOGITS
     uttered
    1.74
     utterance
    1.52
     uttering
    1.48
     spoken
    1.42
     Spoken
    1.24
     utterances
    1.23
     words
    1.23
    spoken
    1.22
    Spoken
    1.22
     speaking
    1.08
    Activations Density 0.466%

    No Known Activations