© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 758
    Prev
    Next
    INDEX
    Explanations

    scientific and technical data, particularly related to measurements and frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stands
    -0.49
    urt
    -0.45
     haban
    -0.45
     Stands
    -0.44
    dates
    -0.44
    сматри
    -0.43
     approaches
    -0.42
     builds
    -0.41
    нти
    -0.41
     næ
    -0.41
    POSITIVE LOGITS
    saraba
    0.88
    __(/*!
    0.85
     propOrder
    0.85
     <=",
    0.83
    IntoConstraints
    0.82
     defaultstate
    0.82
    ANTLR
    0.82
     الرياضيه
    0.81
     CreateTagHelper
    0.78
    олові
    0.75
    Activations Density 0.133%

    No Known Activations