© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13526
    Prev
    Next
    INDEX
    Explanations

    URLs and references to external resources, particularly those related to scripts and libraries

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

    Code snippets with URLs

    np_acts-logits-general · gemini-2.0-flash

    http or https urls

    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
    msgTypes
    -0.50
    <?
    -0.50
    outState
    -0.48
     otomatig
    -0.47
    gonic
    -0.47
    oredCriteria
    -0.46
    verwijspagina
    -0.46
     rodillas
    -0.45
     iconLine
    -0.45
     käytt
    -0.44
    POSITIVE LOGITS
    jsdelivr
    0.57
    anstal
    0.54
    Autoritní
    0.52
    dflare
    0.44
     ExecuteAsync
    0.42
     smtplib
    0.40
     publicly
    0.40
     Nom
    0.39
     streaming
    0.39
    addPreferredGap
    0.39
    Activations Density 0.248%

    No Known Activations