© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 7426
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating lists or parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Gemma example

    No Comments

    Negative Logits
     da
    -0.70
     de
    -0.68
     van
    -0.68
     en
    -0.64
     die
    -0.63
     mit
    -0.63
     las
    -0.62
     O
    -0.62
     dem
    -0.60
     por
    -0.59
    POSITIVE LOGITS
     itſelf
    1.25
     pleaſure
    1.14
    which
    1.09
     moschino
    1.08
     myſelf
    1.06
     doubtnut
    1.06
     greateſt
    1.04
     ſp
    1.03
    !!!)
    1.03
     $_(
    1.02
    Activations Density 0.606%

    No Known Activations