© 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. 12611
    Prev
    Next
    INDEX
    Explanations

    statements about the performance and efficacy of materials in braking systems

    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
    Personendaten
    -0.61
    owska
    -0.52
     useAppContext
    -0.52
    tdessen
    -0.51
    Verkehr
    -0.51
    AndEndTag
    -0.51
    adpleegd
    -0.50
    참고
    -0.49
    öv
    -0.49
     sortes
    -0.49
    POSITIVE LOGITS
     manufacturers
    0.75
     aftermarket
    0.66
     reliability
    0.65
     performance
    0.65
    Manufacturers
    0.64
     anecdotal
    0.63
     manufactures
    0.63
    performance
    0.62
    UnusedPrivate
    0.61
     manufacturer
    0.61
    Activations Density 0.404%

    No Known Activations