© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 16353
    Prev
    Next
    INDEX
    Explanations

    assertions and opinions based on critical thinking and skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumii
    -0.49
    PerformLayout
    -0.45
    олові
    -0.43
     GenerationType
    -0.38
     PeEnEo
    -0.36
    先是
    -0.36
    Dazu
    -0.36
     Савезне
    -0.35
     alors
    -0.34
     खरीदा
    -0.33
    POSITIVE LOGITS
     getting
    1.39
     owning
    1.24
     acquiring
    1.23
     installing
    1.23
     obtaining
    1.23
     having
    1.18
     doing
    1.18
     selecting
    1.17
     choosing
    1.17
     buying
    1.17
    Activations Density 1.132%

    No Known Activations