© 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. 19-GEMMASCOPE-RES-16K
    11. 2456
    Prev
    Next
    INDEX
    Explanations

    references to temporal phrases and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sidemargin
    -0.81
    parsedMessage
    -0.71
    migrationBuilder
    -0.67
    astify
    -0.67
    MemoryWarning
    -0.66
    Française
    -0.65
    
    -0.64
     виправивши
    -0.63
    WithIOException
    -0.62
    OrNil
    -0.62
    POSITIVE LOGITS
     when
    1.21
     whenever
    1.10
    when
    1.09
    whenever
    0.98
     moment
    0.98
    Whenever
    0.98
     khi
    0.95
     quando
    0.94
     Whenever
    0.93
    When
    0.92
    Activations Density 0.227%

    No Known Activations