© 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. 855
    Prev
    Next
    INDEX
    Explanations

    phrases and elements related to data organization and communication structures

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

    Starts with "We", "This", "With", "It", or "http"

    np_acts-logits-general · gemini-2.0-flash

    with http://

    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
    MigrationBuilder
    -0.69
    setViewportView
    -0.65
    webElementXpaths
    -0.57
    ChildScrollView
    -0.54
    탤
    -0.48
     OMIT
    -0.48
     unknownFields
    -0.47
    MergeFrom
    -0.47
    kháu
    -0.47
    vron
    -0.47
    POSITIVE LOGITS
     topik
    0.43
    Fordítás
    0.41
     Bewußt
    0.39
    subplot
    0.38
    Topic
    0.37
     title
    0.36
     Sollte
    0.36
     lemak
    0.36
     Schein
    0.36
    ]")]
    0.36
    Activations Density 0.237%

    No Known Activations