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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 995
    Prev
    Next
    INDEX
    Explanations

    programming constructs, particularly those related to named attributes and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "
    -0.52
     zod
    -0.49
     soon
    -0.45
     about
    -0.45
     it
    -0.44
     relative
    -0.44
     
    -0.43
     “
    -0.42
    ‌پ
    -0.42
    HKEY
    -0.42
    POSITIVE LOGITS
    BeginContext
    1.00
    PerformLayout
    0.90
    ParallelGroup
    0.85
    MigrationBuilder
    0.85
     typelib
    0.84
    
    0.83
    InvalidProtocol
    0.81
    __':
    0.79
     Мексичка
    0.78
    IUrlHelper
    0.77
    Activations Density 0.074%

    No Known Activations