© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 7481
    Prev
    Next
    INDEX
    Explanations

    references to surveillance, secrecy, and information leaking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     akumulator
    -0.28
     produced
    -0.28
    input
    -0.28
    accept
    -0.27
     accepting
    -0.27
     đỉnh
    -0.26
    소
    -0.26
    app
    -0.26
     zakład
    -0.26
     acepta
    -0.25
    POSITIVE LOGITS
     kasarigan
    0.88
     nahilalakip
    0.81
    OGND
    0.79
    MessageOf
    0.77
    tagHelperRunner
    0.73
     autorytatywna
    0.73
    setVerticalGroup
    0.71
    writeFieldEnd
    0.68
    IntoConstraints
    0.67
    NameInMap
    0.67
    Activations Density 0.446%

    No Known Activations