© 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-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 6287
    Prev
    Next
    INDEX
    Explanations

    specific XML schema elements and their configurations related to application programming and task automation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cref
    -0.77
    IBOutlet
    -0.76
    :✨
    -0.62
    ReusableCell
    -0.61
    cibly
    -0.60
    })));
    -0.60
     footh
    -0.59
    ủi
    -0.58
     rho
    -0.57
     Rho
    -0.57
    POSITIVE LOGITS
    EventHandler
    1.23
     ModelExpression
    0.98
    Controllers
    0.86
    CompleteListener
    0.85
    XMLSchema
    0.85
     jsPsych
    0.81
    CodedInputStream
    0.77
     EventHandler
    0.74
    PageContext
    0.72
    SuccessListener
    0.72
    Activations Density 0.010%

    No Known Activations