© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14309
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical typesetting and formatting in LaTeX

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

    LaTeX commands and formatting

    np_acts-logits-general · gemini-2.0-flash

    XML parameters

    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
     Normdatei
    -0.43
     ***!
    -0.41
    Tracce
    -0.35
    xase
    -0.35
    GOTREF
    -0.35
    enterOuterAlt
    -0.35
    TouchListener
    -0.33
    openConnection
    -0.32
    AndroidJUnit
    -0.32
    Tikang
    -0.31
    POSITIVE LOGITS
     saites
    0.54
    xaml
    0.53
     '\\;'
    0.52
     visuals
    0.52
    enumi
    0.51
    Specs
    0.48
     visuel
    0.47
    multicolumn
    0.47
    Sector
    0.47
    Kä
    0.46
    Activations Density 0.046%

    No Known Activations