© 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. 3060
    Prev
    Next
    INDEX
    Explanations

    interactions between characters that convey emotional intimacy

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

    physical movements and actions, particularly verbs describing how people move their bodies through space.

    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
    scribers
    -0.48
    bootstrapcdn
    -0.47
     này
    -0.47
    SBATCH
    -0.45
     priori
    -0.44
     necessariamente
    -0.43
     forcément
    -0.43
    PYX
    -0.43
    Rptr
    -0.43
     podczas
    -0.43
    POSITIVE LOGITS
    GOTREF
    0.55
     bezeichneter
    0.42
     hastily
    0.40
     nearby
    0.39
     AssemblyCulture
    0.37
     iprot
    0.37
     toward
    0.36
     nakalista
    0.36
     motion
    0.36
     бра
    0.36
    Activations Density 0.351%

    No Known Activations