© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3333
    Prev
    Next
    INDEX
    Explanations

    geographical names and administrative divisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    geographical location descriptions in Wikipedia-style articles about places.

    oai_token-act-pair · claude-4-5-haikuTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.74
     Monfieur
    -0.63
     pleaſure
    -0.63
     Houſe
    -0.61
     Majefty
    -0.56
     cæ
    -0.52
     Berlín
    -0.51
     Decken
    -0.50
     Cæsar
    -0.49
     Bauch
    -0.48
    POSITIVE LOGITS
     silenzio
    0.40
     kooper
    0.40
    Otter
    0.40
     argparse
    0.39
     décisions
    0.39
     consommateurs
    0.38
    gameserver
    0.37
     prisonniers
    0.36
     mêmes
    0.35
    msgTypes
    0.35
    Activations Density 0.318%

    No Known Activations