© 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. 3124
    Prev
    Next
    INDEX
    Explanations

    collective pronouns and their associated verbs in discussions about community or group activities

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

    temporal transitions and forward-looking statements that introduce upcoming topics or events.

    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
     однако
    -0.38
     muuta
    -0.38
     joten
    -0.38
     tarko
    -0.35
     jopa
    -0.35
     porém
    -0.35
    udayaan
    -0.35
     kysy
    -0.35
    ниципа
    -0.35
     abstrato
    -0.34
    POSITIVE LOGITS
     progresses
    0.89
    AddTagHelper
    0.84
     nears
    0.82
     prepares
    0.72
     matures
    0.72
     approaches
    0.70
     progressed
    0.70
     continues
    0.69
     struggles
    0.65
     slowly
    0.65
    Activations Density 0.184%

    No Known Activations