© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 251
    Prev
    Next
    INDEX
    Explanations

    PHP code syntax and structures

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

    PHP code block or namespace/use declarations

    np_acts-logits-general · gemini-2.0-flash

    PHP code structure

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    BagConstraints
    -0.70
     صوتيه
    -0.69
     الرياضيه
    -0.63
    PreferredItem
    -0.61
     FetchType
    -0.60
    aimerais
    -0.59
     internetowa
    -0.58
     exemplaires
    -0.58
    UIControlState
    -0.57
    новништво
    -0.57
    POSITIVE LOGITS
    require
    0.67
    Geplaatst
    0.64
    use
    0.64
    include
    0.62
    class
    0.60
    RegistryLite
    0.59
    ini
    0.52
     use
    0.51
    Trait
    0.49
    namespace
    0.48
    Activations Density 0.036%

    No Known Activations