© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 406
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and document structure

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    LaTeX commands starting with backslash

    np_acts-logits-general · gemini-2.0-flash

    LaTeX package commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    MessageTagHelper
    -1.02
     disambiguazione
    -0.93
     queſta
    -0.93
     betweenstory
    -0.89
     kasarigan
    -0.87
    AccessorTable
    -0.87
    NameInMap
    -0.85
    enterOuterAlt
    -0.84
     itſelf
    -0.83
     propOrder
    -0.81
    POSITIVE LOGITS
    .
    0.46
     
    0.43
     T
    0.39
     and
    0.37
     S
    0.36
     $
    0.36
     I
    0.35
     A
    0.35
     W
    0.35
     \
    0.35
    Activations Density 0.020%

    No Known Activations