© 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. 12412
    Prev
    Next
    INDEX
    Explanations

    phrases related to research studies and scientific reports

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

    Appears after prepositions

    np_acts-logits-general · gemini-2.0-flash

    foreign or technical language

    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
     tegens
    -0.35
     kautta
    -0.35
    forhold
    -0.34
    bės
    -0.34
     forhold
    -0.34
     mogelijkheden
    -0.33
    很多
    -0.32
    harapkan
    -0.32
     ways
    -0.32
     are
    -0.32
    POSITIVE LOGITS
    󠁣
    0.95
    ScopeManager
    0.91
     autorytatywna
    0.87
    parsedMessage
    0.86
    ſicht
    0.83
     deſſen
    0.82
     Wikimedijinoj
    0.81
     Мексичка
    0.80
    MLLoader
    0.79
    [@BOS@]
    0.78
    Activations Density 0.637%

    No Known Activations