© 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. 5-GEMMASCOPE-RES-16K
    11. 15607
    Prev
    Next
    INDEX
    Explanations

    references to notable literary or artistic works and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    URLException
    -0.79
     GenerationType
    -0.78
    +:+
    -0.76
     onResponse
    -0.75
    PMailer
    -0.72
    Personensuche
    -0.72
    ReusableCell
    -0.67
     OnDestroy
    -0.67
    etCode
    -0.67
    crisy
    -0.66
    POSITIVE LOGITS
    ETHING
    0.51
    boden
    0.50
    dieron
    0.48
     rangs
    0.48
     borra
    0.48
    мят
    0.46
     DevComponents
    0.46
     сове
    0.45
    Boden
    0.45
    ksom
    0.45
    Activations Density 0.822%

    No Known Activations