© 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. 2-GEMMASCOPE-RES-16K
    11. 5820
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming functions and symmetric/asymmetric properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pulseira
    -0.40
    ázaro
    -0.39
    subs
    -0.38
    jaqueta
    -0.38
     BRIG
    -0.38
     sabem
    -0.37
     Shaft
    -0.36
     Rye
    -0.36
    carpa
    -0.36
    colgante
    -0.36
    POSITIVE LOGITS
     symmetric
    0.84
     Lightning
    0.75
     Thunder
    0.74
     lightning
    0.74
     bolt
    0.74
     Symmetric
    0.71
    symmetric
    0.69
     asymmetric
    0.68
    Thunder
    0.67
    Lightning
    0.67
    Activations Density 0.291%

    No Known Activations