© 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. 35-GEMMASCOPE-RES-16K
    11. 7655
    Prev
    Next
    INDEX
    Explanations

    references to British entities or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inigte
    -0.53
     Haitian
    -0.48
    万美元
    -0.47
    atecas
    -0.46
    SequentialGroup
    -0.43
    ronesia
    -0.41
     صوتيه
    -0.41
     maș
    -0.41
     tramonto
    -0.40
     Kinney
    -0.40
    POSITIVE LOGITS
     British
    2.20
     Britain
    2.13
     England
    2.13
     UK
    2.13
    英国
    2.06
    British
    2.02
    Britain
    1.94
     british
    1.92
     Britons
    1.91
    England
    1.90
    Activations Density 1.285%

    No Known Activations