© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 3526
    Prev
    Next
    INDEX
    Explanations

    references to wings and their attachments in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.48
     tatuagens
    -0.45
    zeiten
    -0.45
     rahasia
    -0.45
     Kelurahan
    -0.45
    为例
    -0.41
     tempio
    -0.40
     transférez
    -0.40
     creciendo
    -0.40
     marrom
    -0.40
    POSITIVE LOGITS
    Attach
    0.68
    attach
    0.65
    Attachment
    0.63
     Wing
    0.59
     Attachment
    0.59
    Wing
    0.58
     WING
    0.58
     wing
    0.58
     Attach
    0.57
    enumi
    0.56
    Activations Density 1.146%

    No Known Activations