© 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-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 12270
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate conditions or qualifications in a statement

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ########.
    -0.73
     ―――――
    -0.64
     houſe
    -0.60
     kasarigan
    -0.60
     esternos
    -0.60
    DockStyle
    -0.59
    +:+
    -0.59
    iſchen
    -0.59
    findpost
    -0.59
     faſt
    -0.58
    POSITIVE LOGITS
    Which
    0.70
     Which
    0.68
     vilket
    0.65
     WHICH
    0.63
     hvilket
    0.59
    which
    0.59
     což
    0.59
     which
    0.56
     οποίο
    0.54
     lesquelles
    0.50
    Activations Density 0.424%

    No Known Activations