© 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. 23-GEMMASCOPE-RES-16K
    11. 6257
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "cause" and its variations, particularly in contexts relating to negative outcomes or problems

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    RDP
    -0.51
     Westminster
    -0.48
    hline
    -0.47
    berton
    -0.47
    ¯¯
    -0.46
    alagi
    -0.42
    EFIAPI
    -0.42
    JMenuBar
    -0.42
     Román
    -0.41
    byter
    -0.41
    POSITIVE LOGITS
     Cause
    1.25
     caused
    1.19
     CAUSE
    1.17
     cause
    1.13
     Caused
    1.13
    caused
    1.10
     Causes
    1.08
    Cause
    1.07
    cause
    1.07
     causing
    1.07
    Activations Density 0.222%

    No Known Activations