© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 14970
    Prev
    Next
    INDEX
    Explanations

    key phrases indicating conclusions or recommendations based on data analysis

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

    something

    np_acts-logits-general · gemini-2.0-flash

    suggests or indicates a conclusion

    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
     nhàng
    -0.45
    NOW
    -0.43
    EDEFAULT
    -0.42
    IUrlHelper
    -0.42
     okuyayım
    -0.41
     Stok
    -0.41
    styleType
    -0.41
    aglio
    -0.41
     lau
    -0.40
     experimentally
    -0.40
    POSITIVE LOGITS
    #
    0.39
    それだけ
    0.38
     Италијани
    0.37
     FetchType
    0.37
     aDecoder
    0.36
     Folge
    0.36
     Italijani
    0.34
    principalTable
    0.33
    ValueGeneration
    0.33
    SharedDtor
    0.33
    Activations Density 0.833%

    No Known Activations