© 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. 14051
    Prev
    Next
    INDEX
    Explanations

    references to scientific concepts and terminology

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

    Followed by prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    amounts, downs, legends, configuration

    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
    EndInit
    -0.60
     nonUne
    -0.54
    IGraphics
    -0.54
     ivelany
    -0.53
     resourceCulture
    -0.52
    úgó
    -0.52
    zeera
    -0.51
    Descarga
    -0.48
    kháu
    -0.48
    BeginInit
    -0.47
    POSITIVE LOGITS
    发表于
    0.38
    あって
    0.33
    AutoScaleMode
    0.32
    Vielen
    0.32
     <=",
    0.32
    ApiOperation
    0.32
     endregion
    0.31
     uğ
    0.31
     nacionales
    0.31
     diferencia
    0.31
    Activations Density 0.121%

    No Known Activations