© 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. 0-GEMMASCOPE-RES-16K
    11. 2807
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or organizations

    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
    LEncoder
    -0.54
    protoimpl
    -0.51
     Numerade
    -0.48
    AlterField
    -0.47
    aarrggbb
    -0.44
    BagLayout
    -0.43
    
    -0.41
    iostream
    -0.40
    RegistryLite
    -0.40
    XmlType
    -0.39
    POSITIVE LOGITS
     duties
    0.65
     Launching
    0.60
     Launch
    0.59
    Launch
    0.59
    rungsseite
    0.56
     Capability
    0.56
    Capability
    0.55
    ientras
    0.54
     launching
    0.54
     Duties
    0.53
    Activations Density 0.197%

    No Known Activations