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. 23-GEMMASCOPE-RES-16K
    6. 9132
    Prev
    Next
    INDEX
    Explanations

    terminology related to database operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StatefulWidget
    -0.70
    PyExc
    -0.59
    ContentAsync
    -0.56
     estimés
    -0.56
    ValueStyle
    -0.53
     AssemblyTitle
    -0.52
     gynhyrchwyd
    -0.52
    jsonwebtoken
    -0.52
     للمعارف
    -0.51
    RLock
    -0.51
    POSITIVE LOGITS
     removal
    2.94
     remove
    2.77
     removing
    2.73
     removed
    2.65
     Removal
    2.65
     Removing
    2.51
     Remove
    2.50
     removes
    2.42
    removal
    2.40
    Removing
    2.39
    Activations Density 1.154%

    No Known Activations