© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 11494
    Prev
    Next
    INDEX
    Explanations

    specific characters and symbols from multiple languages

    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
    notations
    -0.46
    IBILITIES
    -0.45
    lidades
    -0.45
     Numerade
    -0.44
    msgTypes
    -0.44
    elve
    -0.44
    Descriptions
    -0.43
    itaries
    -0.43
     revers
    -0.42
     legitim
    -0.42
    POSITIVE LOGITS
    原始内容存档
    0.44
    fjspx
    0.43
     femininas
    0.43
     feminina
    0.41
     vectorielle
    0.39
     femininos
    0.38
    DECREF
    0.38
    arriver
    0.37
     spécifique
    0.36
     @"/
    0.35
    Activations Density 0.054%

    No Known Activations