© 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. 4026
    Prev
    Next
    INDEX
    Explanations

    references to personal identity and self-expression

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

    often followed by a comma

    np_acts-logits-general · gemini-2.0-flash

    names of places or brands

    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
    InputTagHelper
    -0.54
     jspb
    -0.52
     FetchType
    -0.52
     jsPsych
    -0.51
    ViewImports
    -0.50
    verifyException
    -0.50
    weightedMode
    -0.50
    Бахар
    -0.49
    Espèce
    -0.48
    archiviato
    -0.48
    POSITIVE LOGITS
     alone
    0.41
     plenamente
    0.37
     lisäksi
    0.34
     plus
    0.34
     pleinement
    0.32
    ppuden
    0.31
     surrounded
    0.31
     eminently
    0.30
     कीजिए
    0.30
     traditionally
    0.30
    Activations Density 0.534%

    No Known Activations