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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 8327
    Prev
    Next
    INDEX
    Explanations

    references to apples and related products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ніципа
    -0.38
     Grot
    -0.38
    RefNanny
    -0.38
     קו
    -0.38
    Ist
    -0.36
    出版年
    -0.36
    mogorov
    -0.36
     Klaus
    -0.35
     Jeffery
    -0.35
    otrop
    -0.35
    POSITIVE LOGITS
     apple
    2.27
     Apple
    2.17
    Apple
    2.03
     apples
    1.98
    apple
    1.92
     APPLE
    1.88
     Apples
    1.79
    APPLE
    1.63
    苹果
    1.63
    Apples
    1.62
    Activations Density 0.162%

    No Known Activations