© 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
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15593
    Prev
    Next
    INDEX
    Explanations

    references to quizzes, cases, campaigns, and data structures within a technical or legal context

    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
    тистика
    -0.39
    GOTREF
    -0.38
     unknownFields
    -0.35
     penjualan
    -0.35
     stink
    -0.34
     actuel
    -0.33
     whole
    -0.33
    führt
    -0.33
     المال
    -0.32
    OGND
    -0.32
    POSITIVE LOGITS
     disambiguazione
    0.69
    rungsseite
    0.68
     betweenstory
    0.59
     AssemblyTitle
    0.57
    esModule
    0.57
     kasarigan
    0.55
    +#+
    0.53
     AssemblyCompany
    0.53
    tinyos
    0.52
     ſever
    0.49
    Activations Density 0.898%

    No Known Activations