Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9170
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "past"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kugel
    -0.87
     Richelieu
    -0.83
     CDP
    -0.83
    afficheront
    -0.83
     Jeanette
    -0.82
     Sardinia
    -0.80
     Belleville
    -0.80
     Garibaldi
    -0.79
     Eisenberg
    -0.79
     Doria
    -0.78
    POSITIVE LOGITS
     Past
    1.78
    Past
    1.65
     past
    1.63
    past
    1.54
    PAST
    1.49
     PAST
    1.48
     Pasture
    0.85
     Pas
    0.84
     passato
    0.81
    >*/
    0.76
    Activations Density 0.037%

    No Known Activations