© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 354
    Prev
    Next
    INDEX
    Explanations

    phrases indicating updates and information sharing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <>",
    -0.59
    openConnection
    -0.58
    URLException
    -0.57
     faktisk
    -0.56
     Autres
    -0.54
     Houſe
    -0.53
     ―――――
    -0.51
    wot
    -0.51
     EFE
    -0.51
     lenger
    -0.50
    POSITIVE LOGITS
    Становништво
    0.53
     sớm
    0.50
    ViewFeatures
    0.49
    ורות
    0.49
     Soon
    0.49
     updates
    0.49
    Soon
    0.49
    IVEREF
    0.48
    وفير
    0.48
     update
    0.47
    Activations Density 0.211%

    No Known Activations