© 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. 15740
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands related to document formatting and structure

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

    LaTeX and mathematical typesetting commands and syntax.

    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
     ogen
    -0.35
     unknownFields
    -0.32
     Gelegenheit
    -0.32
     broek
    -0.31
    ComponentModel
    -0.30
     rzecz
    -0.30
    =-=-=-=-
    -0.29
    obe
    -0.29
     سبيل
    -0.28
    valueOf
    -0.28
    POSITIVE LOGITS
    хьтан
    0.66
    RTEX
    0.63
     مرئيه
    0.62
    enumii
    0.62
     &___
    0.61
    
    0.61
    Espèce
    0.60
    səhifə
    0.59
     transférez
    0.59
    transQ
    0.59
    Activations Density 0.702%

    No Known Activations