© 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. 2-GEMMASCOPE-RES-16K
    11. 4898
    Prev
    Next
    INDEX
    Explanations

    references to premises, particularly in a legal or formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ال
    -0.62
     دیکھیے
    -0.61
     Den
    -0.59
    totta
    -0.57
    Quellen
    -0.56
    prisingly
    -0.56
    Source
    -0.56
    BarItem
    -0.55
     po
    -0.54
    شهاد
    -0.54
    POSITIVE LOGITS
     Premises
    1.21
     premises
    1.17
     myſelf
    1.01
     premise
    0.93
     itſelf
    0.87
    Precalculus
    0.85
    premises
    0.82
    oneofs
    0.81
    Premise
    0.79
    PREDICT
    0.78
    Activations Density 0.044%

    No Known Activations