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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6592
    Prev
    Next
    INDEX
    Explanations

    technical jargon and processes related to manufacturing and material science

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

    descriptions of mechanical processes or physical actions involving motion or force.

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

    sequences describing mechanical or process steps with high-activation words indicating sequential actions and transformations.

    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
     underwent
    -0.43
    DeleteBehavior
    -0.40
    WithMany
    -0.39
     thrives
    -0.39
     undergoes
    -0.38
     thrive
    -0.37
    CONTINUE
    -0.37
     predictor
    -0.37
     отли
    -0.37
     acompaña
    -0.36
    POSITIVE LOGITS
     mengubah
    0.68
     activate
    0.67
     bringing
    0.67
     bring
    0.66
     causing
    0.63
     causes
    0.63
    bringing
    0.62
     obliter
    0.62
     activating
    0.61
     deple
    0.61
    Activations Density 1.426%

    No Known Activations