© 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. 5742
    Prev
    Next
    INDEX
    Explanations

    specific product comparisons and preferences related to electronic devices

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

    first-person statements where the writer is expressing personal opinions or experiences, particularly following periods or commas.

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

    personal subjective opinions and experiences expressed through first-person narrative.

    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
    localctx
    -0.50
    Контак
    -0.41
     aplic
    -0.39
    <?
    -0.39
     tror
    -0.39
    Apparently
    -0.39
     arrests
    -0.38
     apla
    -0.38
     bluzka
    -0.38
     interpretation
    -0.37
    POSITIVE LOGITS
     upgrading
    0.85
     upgrade
    0.83
    upgrade
    0.74
     upgrades
    0.72
     upgraded
    0.68
     Upgrade
    0.66
    Upgrade
    0.65
     Upgrades
    0.65
     purchasing
    0.64
     purchased
    0.63
    Activations Density 0.384%

    No Known Activations