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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 15284
    Prev
    Next
    INDEX
    Explanations

    statistical analysis methods and terms used in research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.46
    toThrow
    -0.44
    الإنجليزية
    -0.44
     Obrador
    -0.42
    ativement
    -0.42
     PhpStorm
    -0.42
     Recognizing
    -0.41
     ligiloj
    -0.41
    pencer
    -0.41
     spec
    -0.41
    POSITIVE LOGITS
     Réponses
    0.53
     necesite
    0.40
     <=",
    0.40
    原始内容存档于
    0.40
    testify
    0.39
    endpush
    0.39
     normalidad
    0.39
    httphttps
    0.37
     medida
    0.35
    InjectAttribute
    0.34
    Activations Density 1.711%

    No Known Activations