© 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. 10-GEMMASCOPE-RES-16K
    11. 2810
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "affect" or its variations, particularly in the context of identifying causes and effects

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ändigt
    -0.34
    ließlich
    -0.32
     flip
    -0.31
    FlatAppearance
    -0.31
    unzi
    -0.29
    Occasionally
    -0.29
     său
    -0.28
     Außer
    -0.28
    Nome
    -0.27
    Flip
    -0.27
    POSITIVE LOGITS
     affected
    1.61
     Affected
    1.51
    affected
    1.51
     AFFECT
    1.45
     affecting
    1.41
     affects
    1.40
    Affected
    1.40
    affect
    1.38
     affect
    1.36
     Affecting
    1.36
    Activations Density 0.413%

    No Known Activations