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. 10-GEMMASCOPE-RES-16K
    6. 2753
    Prev
    Next
    INDEX
    Explanations

    sentences containing significant chronological or sequential events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.84
     cherchés
    -0.81
     HasFactory
    -0.80
    IsMutable
    -0.72
    }`}>
    -0.70
    ReusableCell
    -0.70
     InputDecoration
    -0.68
     useHistory
    -0.65
    مصادر
    -0.65
     kasarigan
    -0.65
    POSITIVE LOGITS
    Then
    0.74
     Then
    0.69
     then
    0.66
    then
    0.60
     THEN
    0.53
     lalu
    0.52
     whereupon
    0.51
     Thereafter
    0.47
     kemudian
    0.47
     sonra
    0.46
    Activations Density 0.461%

    No Known Activations