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-2-2B
    4. Residual Stream - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 58493
    Prev
    Next
    INDEX
    Explanations

    parameters and characteristics related to clock speed and synchronization in electronic systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    msgTypes
    -0.59
     tả
    -0.55
     pan
    -0.53
    客
    -0.49
    행
    -0.47
     ba
    -0.47
    gri
    -0.47
    ktop
    -0.46
    fico
    -0.46
    vue
    -0.46
    POSITIVE LOGITS
    aarrggbb
    0.85
     rospy
    0.81
     CLK
    0.78
    migrationBuilder
    0.75
    SequentialGroup
    0.73
     clk
    0.73
     clocks
    0.71
    Begriffsklä
    0.70
     Clocks
    0.69
     horloge
    0.68
    Activations Density 0.048%

    No Known Activations