© 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. 3-GEMMASCOPE-RES-16K
    11. 9459
    Prev
    Next
    INDEX
    Explanations

    instances of the term "quad" or varying spacing characters typical in mathematical formats

    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
    deepcopy
    -0.38
     copy
    -0.36
     Cohn
    -0.35
    findBy
    -0.33
     proof
    -0.31
    $_
    -0.31
     amor
    -0.31
     pedagog
    -0.31
     spo
    -0.31
     barra
    -0.31
    POSITIVE LOGITS
    quad
    2.05
     quad
    2.02
     Quad
    1.90
    Quad
    1.76
    QUAD
    1.42
     quads
    1.34
     quadru
    1.10
     cuad
    1.09
     quadri
    1.05
     quadruple
    1.02
    Activations Density 0.050%

    No Known Activations