© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14779
    Prev
    Next
    INDEX
    Explanations

    instances of data assignment and manipulation in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The token "data" is being written

    np_acts-logits-general · gemini-2.0-flash

    writing data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.58
     rodilla
    -0.53
     cremallera
    -0.53
     reputación
    -0.52
     atracción
    -0.52
     certificación
    -0.52
     colgante
    -0.51
     excepción
    -0.51
     plegable
    -0.51
     reparación
    -0.50
    POSITIVE LOGITS
     Data
    1.42
     data
    1.30
     DATA
    1.26
    Data
    1.23
    data
    1.20
    DATA
    1.14
     getData
    1.03
     Datas
    1.03
     datas
    1.02
     GetData
    1.00
    Activations Density 0.156%

    No Known Activations