© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11523
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and structures

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

    Code, structures, or mathematical formulas

    np_acts-logits-general · gemini-2.0-flash

    paddle for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.70
    enterOuterAlt
    -0.66
     jScrollPane
    -0.63
     pinulongan
    -0.58
    DockStyle
    -0.56
    EndContext
    -0.54
     Мексичка
    -0.49
    ſelf
    -0.49
    rrggbb
    -0.49
    lwjgl
    -0.48
    POSITIVE LOGITS
     introductory
    0.36
    ゚)
    0.35
    Introductory
    0.34
    gridColumn
    0.33
     Introductory
    0.33
     Grat
    0.31
    ***************/
    0.30
     heavily
    0.30
    pers
    0.29
     Central
    0.29
    Activations Density 1.157%

    No Known Activations