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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 53922
    Prev
    Next
    INDEX
    Explanations

    concepts related to time travel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.60
     insuffisamment
    -0.56
    AnchorStyles
    -0.56
     esternos
    -0.55
     defaultstate
    -0.53
     للاسماء
    -0.51
    ktop
    -0.47
     initComponents
    -0.47
     ujednoznacz
    -0.47
    PIP
    -0.46
    POSITIVE LOGITS
     history
    0.49
    SceneManagement
    0.47
     time
    0.45
    UpdateCommand
    0.43
     backward
    0.42
     Wayback
    0.42
     preservation
    0.42
     timeline
    0.40
     HISTORY
    0.40
    HISTORY
    0.40
    Activations Density 0.014%

    No Known Activations