© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16328
    Prev
    Next
    INDEX
    Explanations

    references to authority and official status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nebraska
    -0.48
     Sandler
    -0.47
    razine
    -0.45
     yyr
    -0.45
    Égypte
    -0.44
     przeds
    -0.42
    agoza
    -0.42
    Spider
    -0.42
     Grüsse
    -0.42
    Yorkshire
    -0.42
    POSITIVE LOGITS
     Official
    0.90
     Offic
    0.84
     official
    0.83
    offic
    0.79
     offici
    0.79
     offic
    0.78
    Official
    0.78
     officials
    0.76
     OFFIC
    0.76
     OFFICIAL
    0.76
    Activations Density 0.087%

    No Known Activations