© 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. 25-GEMMASCOPE-RES-16K
    11. 15965
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to networking and data transmission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Small
    -0.98
     Regular
    -0.95
     Remote
    -0.95
     Large
    -0.94
     Short
    -0.92
    Small
    -0.92
     Permanent
    -0.92
     Traditional
    -0.91
    Remote
    -0.90
     Minimal
    -0.90
    POSITIVE LOGITS
    You
    0.56
     Story
    0.56
     You
    0.55
     Song
    0.52
     Says
    0.52
     Answer
    0.51
    AccessFile
    0.50
     Songs
    0.50
     Stuff
    0.49
    Questions
    0.49
    Activations Density 6.614%

    No Known Activations