© 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. 15086
    Prev
    Next
    INDEX
    Explanations

    structured data related to artists or items in an API format

    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
     pleaſure
    -0.79
     occafion
    -0.63
     purpoſe
    -0.61
     myſelf
    -0.60
     MainAxisSize
    -0.59
     itſelf
    -0.59
     JpaRepository
    -0.59
    kuuta
    -0.57
    HomeAsUpEnabled
    -0.57
    transQ
    -0.57
    POSITIVE LOGITS
     Retina
    0.46
    bibfield
    0.45
    bibinfo
    0.45
     Carney
    0.44
     proxy
    0.41
    ACHEL
    0.41
     Visitation
    0.41
     listed
    0.41
     notable
    0.41
     remarkable
    0.41
    Activations Density 1.503%

    No Known Activations