© 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-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 11754
    Prev
    Next
    INDEX
    Explanations

    instructions or questions related to profile management and user actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portály
    -0.62
     rubbed
    -0.60
     rubs
    -0.59
    providedIn
    -0.58
    Portale
    -0.57
     MongoClient
    -0.57
    Portail
    -0.56
    ound
    -0.54
     concentrates
    -0.54
     chewed
    -0.54
    POSITIVE LOGITS
     view
    0.66
     AssemblyTitle
    0.64
     copy
    0.60
     manually
    0.58
     access
    0.58
     specify
    0.56
     delete
    0.55
     save
    0.53
     switch
    0.53
     obtain
    0.52
    Activations Density 0.410%

    No Known Activations