© 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
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 14599
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to evaluation and performance assessment in models and experiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.70
    bootstrapcdn
    -0.69
    :✨
    -0.69
     فريبيس
    -0.66
    httphttps
    -0.64
     snippetHide
    -0.63
    UnsafeEnabled
    -0.63
    Personendaten
    -0.62
    TagMode
    -0.62
     चीज़ों
    -0.60
    POSITIVE LOGITS
    CDCl
    0.48
     huelga
    0.45
     pungkas
    0.43
    typeorm
    0.42
     klikken
    0.41
    ientôt
    0.39
    řeb
    0.38
    igenschaften
    0.36
     geladeira
    0.36
     trekken
    0.36
    Activations Density 2.035%

    No Known Activations