© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 2838
    Prev
    Next
    INDEX
    Explanations

    references to dirt and its associated complexities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 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
     Ade
    -0.59
     Fros
    -0.59
     Cott
    -0.58
    Nuorodos
    -0.57
    WireFormatLite
    -0.57
    限り
    -0.56
    Yu
    -0.55
     considérons
    -0.55
    ssf
    -0.54
    rog
    -0.54
    POSITIVE LOGITS
     dirty
    1.02
     dirt
    1.00
    dirty
    0.91
     Dirt
    0.89
     Dirty
    0.88
    Dirt
    0.88
    Dirty
    0.86
    dirt
    0.86
     pupil
    0.82
     Burial
    0.81
    Activations Density 0.134%

    No Known Activations