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. 11611
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation in the text

    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
    MigrationBuilder
    -0.73
     initComponents
    -0.71
     hu
    -0.71
    bootstrapcdn
    -0.70
     Turbul
    -0.68
     Sprinkle
    -0.65
    ItemLayout
    -0.64
     pu
    -0.63
     gainera
    -0.63
     ha
    -0.63
    POSITIVE LOGITS
     myſelf
    1.10
     Monfieur
    1.08
     Jefus
    1.07
     Houſe
    1.07
     himſelf
    1.04
    ſelf
    1.00
     themſelves
    0.99
     itſelf
    0.99
     Anſ
    0.97
     Chriftian
    0.94
    Activations Density 0.569%

    No Known Activations