© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 15916
    Prev
    Next
    INDEX
    Explanations

    phrases referring to actions or events that occur subsequently, particularly those involving legal or social consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     actuels
    -0.78
    andaag
    -0.75
    horabuena
    -0.75
     незавершена
    -0.72
     actuelles
    -0.70
     vectorielles
    -0.70
     automatiques
    -0.68
     humaines
    -0.66
     particuliers
    -0.65
     particulières
    -0.65
    POSITIVE LOGITS
     later
    0.89
     Later
    0.87
    Later
    0.85
     LATER
    0.77
    later
    0.76
     Posteriormente
    0.75
     posteriormente
    0.73
     später
    0.67
     позже
    0.66
     subsequent
    0.62
    Activations Density 0.078%

    No Known Activations