© 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. 3078
    Prev
    Next
    INDEX
    Explanations

    references to caves and cave-related terminology

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

    references to caves.

    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
     sunburn
    -0.40
     numerator
    -0.34
     Fence
    -0.32
     PeEnEo
    -0.32
     defoli
    -0.32
     sund
    -0.31
    solar
    -0.30
     جام
    -0.30
    pesar
    -0.30
     Tack
    -0.29
    POSITIVE LOGITS
     underground
    1.59
     cave
    1.53
     caves
    1.46
     subterranean
    1.41
     tunnels
    1.38
     tunnel
    1.34
     caverns
    1.30
     subterrá
    1.29
    underground
    1.25
     Cave
    1.23
    Activations Density 0.218%

    No Known Activations