© 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. 11-GEMMASCOPE-RES-16K
    11. 10032
    Prev
    Next
    INDEX
    Explanations

    statistical analysis methods and their corresponding significance values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defStyleAttr
    -0.45
    GOTREF
    -0.40
     affatto
    -0.38
    itoba
    -0.37
    iphery
    -0.35
    komt
    -0.35
    諺
    -0.35
    软件特色
    -0.35
     valmis
    -0.35
    WindowConstants
    -0.34
    POSITIVE LOGITS
    SequentialGroup
    0.71
     محفوظة
    0.57
    shadowOffset
    0.55
    findpost
    0.52
    ьаж
    0.45
     fodder
    0.45
     للمعارف
    0.45
    }])
    0.44
    DockStyle
    0.44
    atimes
    0.43
    Activations Density 1.144%

    No Known Activations