© 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. 31-GEMMASCOPE-RES-16K
    11. 2947
    Prev
    Next
    INDEX
    Explanations

    references to upper and lower bounds in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    phrases containing the word "upper" especially when referring to mathematical upper bounds or physical upper regions.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi

    the word "upper" in various contexts across different document types.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    addContainerGap
    -0.53
    eschön
    -0.40
    GOTO
    -0.40
    niosek
    -0.40
    AISSEE
    -0.40
     geschehen
    -0.39
     voeten
    -0.39
    lgari
    -0.39
    Sink
    -0.39
    CreateModel
    -0.39
    POSITIVE LOGITS
     Upper
    0.81
     UPPER
    0.73
    Upper
    0.72
     upper
    0.71
    upper
    0.66
     Lower
    0.59
    Personendaten
    0.58
    UPPER
    0.54
    LOWER
    0.52
    Lower
    0.49
    Activations Density 0.215%

    No Known Activations