© 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. 4103
    Prev
    Next
    INDEX
    Explanations

    terms related to electrical components and their specifications in power systems

    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
    ThroughAttribute
    -0.63
    bitField
    -0.62
    alen
    -0.56
     Van
    -0.56
     –
    -0.54
    AutoScaleMode
    -0.54
     -=
    -0.53
    theilung
    -0.53
     van
    -0.53
     kor
    -0.52
    POSITIVE LOGITS
     Efq
    0.98
     myſelf
    0.80
     photolibrary
    0.80
     itſelf
    0.78
     fubject
    0.78
     Shakspeare
    0.66
     Jefus
    0.66
     againſt
    0.66
     oars
    0.65
     becauſe
    0.64
    Activations Density 0.176%

    No Known Activations