© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 7991
    Prev
    Next
    INDEX
    Explanations

    patterns of whitespace and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
     nakalista
    -0.55
     cold
    -0.54
    WriteAttribute
    -0.54
    ecé
    -0.52
     Piccolo
    -0.51
    fea
    -0.51
    cold
    -0.51
     behalf
    -0.49
     fieldNum
    -0.49
     kú
    -0.49
    POSITIVE LOGITS
    存于互联网档案馆
    0.67
     Wikispecies
    0.66
    GORITH
    0.54
    válasz
    0.53
    Beijinhos
    0.52
     = 
    0.52
     eléctricos
    0.51
    verlag
    0.51
     invokingState
    0.51
    LikeLike
    0.50
    Activations Density 0.458%

    No Known Activations