© 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. 3-GEMMASCOPE-RES-16K
    11. 10501
    Prev
    Next
    INDEX
    Explanations

    specific character sequences or patterns in text, often related to coding or mathematical notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deu
    -0.43
    olella
    -0.39
     plotter
    -0.38
    AISSEE
    -0.38
     MwSt
    -0.37
    StreetMap
    -0.37
     wound
    -0.37
    elus
    -0.37
    Movement
    -0.37
    poptotic
    -0.36
    POSITIVE LOGITS
    ee
    1.33
    EE
    1.20
    ees
    1.02
     EE
    0.98
     ee
    0.98
    ее
    0.89
    EES
    0.78
    Ee
    0.75
    eee
    0.73
    EEE
    0.71
    Activations Density 1.142%

    No Known Activations