© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 650
    Prev
    Next
    INDEX
    Explanations

    elements related to complex systems and networks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to biking and bike paths within a specific county

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    network and system contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    TagMode
    -0.59
    клопе
    -0.49
     actionTypes
    -0.45
    jss
    -0.44
     Flücht
    -0.44
    ArrowToggle
    -0.42
    ᵕ
    -0.42
    vericks
    -0.42
    jar
    -0.41
    ρίς
    -0.41
    POSITIVE LOGITS
     network
    2.15
     networks
    1.80
    network
    1.77
     réseau
    1.73
     Network
    1.56
     system
    1.52
    Network
    1.51
     NETWORK
    1.49
    networks
    1.38
     infrastructure
    1.36
    Activations Density 0.236%

    No Known Activations