© 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. 15-GEMMASCOPE-RES-16K
    11. 4300
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to data processing and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LogFactory
    -0.75
    ↵↵↵
    -0.58
     JpaRepository
    -0.51
    printStackTrace
    -0.50
    #![
    -0.48
    findpost
    -0.48
    <i>
    -0.48
     BoxFit
    -0.48
    ↵↵
    -0.47
    ts
    -0.47
    POSITIVE LOGITS
     myſelf
    1.18
     pleaſure
    1.09
     ſta
    0.98
     Monfieur
    0.98
     itſelf
    0.97
     purpoſe
    0.97
     themſelves
    0.95
     Theſe
    0.92
     ſtate
    0.91
     juſ
    0.91
    Activations Density 3.011%

    No Known Activations