© 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. 16-GEMMASCOPE-RES-16K
    11. 12995
    Prev
    Next
    INDEX
    Explanations

    concerns about surveillance and privacy rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itinéraire
    -0.73
    MLLoader
    -0.72
    parsedMessage
    -0.72
    ItemBackground
    -0.69
    writeFieldEnd
    -0.66
    хьтан
    -0.65
    RTGC
    -0.65
    adaptiveStyles
    -0.64
    StoryboardSegue
    -0.64
    Хьажоргаш
    -0.63
    POSITIVE LOGITS
     argument
    0.39
     justification
    0.35
    2
    0.35
     Begründung
    0.35
     zelve
    0.33
     arguments
    0.33
    I
    0.32
    SystemColors
    0.31
     voorbij
    0.31
    W
    0.31
    Activations Density 0.459%

    No Known Activations