© 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-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 515
    Prev
    Next
    INDEX
    Explanations

    references to fields in a data structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sekitarnya
    -0.38
     dalej
    -0.38
    ępu
    -0.35
    operable
    -0.35
    definitely
    -0.35
     económico
    -0.34
    uno
    -0.33
    jug
    -0.33
    roupe
    -0.32
    nps
    -0.32
    POSITIVE LOGITS
     field
    1.66
     fields
    1.60
    Fields
    1.55
    Field
    1.52
     Field
    1.48
     Fields
    1.45
    fields
    1.42
     FIELD
    1.38
    getField
    1.33
     getField
    1.29
    Activations Density 0.300%

    No Known Activations