© 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. 22-GEMMASCOPE-RES-16K
    11. 15103
    Prev
    Next
    INDEX
    Explanations

    HTML or XML encoded entities and markup syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Alloy
    -0.49
     아니라
    -0.48
     Johansson
    -0.48
    Démographie
    -0.47
    Chloroform
    -0.46
    <eos>
    -0.45
    SMP
    -0.45
    iecie
    -0.44
     Alloy
    -0.44
     của
    -0.44
    POSITIVE LOGITS
     avoient
    0.69
     głó
    0.66
     referrerpolicy
    0.64
    parsedMessage
    0.64
     zijne
    0.64
     termica
    0.63
     myö
    0.62
     étoient
    0.59
     ſich
    0.59
     păr
    0.58
    Activations Density 0.351%

    No Known Activations