© 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. 4-GEMMASCOPE-RES-16K
    11. 1745
    Prev
    Next
    INDEX
    Explanations

    phrases that include the phrase "of course."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    namic
    -0.59
    깥
    -0.57
    ishman
    -0.54
     (£
    -0.54
     eficientes
    -0.53
     lading
    -0.50
    ]")]
    -0.50
    ]<<"
    -0.50
    ReactDOM
    -0.49
    aternion
    -0.49
    POSITIVE LOGITS
    følgelig
    1.37
    verständlich
    1.34
     ovviamente
    1.18
     natürlich
    1.17
     Natürlich
    1.15
    czywiście
    1.15
     natuurlijk
    1.14
    eraard
    1.11
     obviously
    1.09
     obviamente
    1.07
    Activations Density 0.251%

    No Known Activations