© 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. 2347
    Prev
    Next
    INDEX
    Explanations

    terms related to web usability and user experience

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

    commas and punctuation separating clauses or list items.

    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
    Pranala
    -0.36
    <caption>
    -0.36
    何より
    -0.36
     PeEnEo
    -0.35
    findpost
    -0.35
     stb
    -0.33
    $+\
    -0.33
     (?)
    -0.32
     (!)
    -0.31
    本当は
    -0.31
    POSITIVE LOGITS
     whether
    3.19
    whether
    2.83
     Whether
    2.70
    Whether
    2.67
     WHETHER
    2.41
     regardless
    2.02
    regardless
    1.91
    不管是
    1.83
     سواء
    1.81
     irrespective
    1.79
    Activations Density 0.602%

    No Known Activations