© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 38629
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting in the text, particularly around code and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndContext
    -0.81
    protoimpl
    -0.77
    новништво
    -0.71
    modelBuilder
    -0.67
     UnityEditor
    -0.66
    enumii
    -0.65
    tvguidetime
    -0.64
    uleiro
    -0.61
    JsonPropertyName
    -0.59
     وتسجيلات
    -0.59
    POSITIVE LOGITS
     للمعارف
    0.50
    :✨
    0.45
     staan
    0.45
    ·
    0.45
    นี้
    0.44
    szön
    0.43
    यी
    0.43
    ืม
    0.43
     başına
    0.42
     jakości
    0.42
    Activations Density 0.061%

    No Known Activations