© 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. 19-GEMMASCOPE-RES-16K
    11. 8581
    Prev
    Next
    INDEX
    Explanations

    instances of the word "discussion" and its variations, indicating a focus on discourse or dialogue

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    whelmed
    -0.59
    inella
    -0.55
     الوطنيه
    -0.52
    t
    -0.51
    jší
    -0.48
    deau
    -0.47
    ezers
    -0.46
     yoke
    -0.44
    FLICT
    -0.43
    newcommand
    -0.43
    POSITIVE LOGITS
     betweenstory
    0.95
     discus
    0.91
     discuss
    0.90
    verwijspagina
    0.90
     Discuss
    0.84
     discusses
    0.84
     discussion
    0.84
    tanleria
    0.82
    ViewFeatures
    0.82
     transfieras
    0.81
    Activations Density 0.079%

    No Known Activations