© 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. 569
    Prev
    Next
    INDEX
    Explanations

    references to knowledge acquisition and sharing in various contexts

    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
    AndEndTag
    -0.52
    Traducción
    -0.50
    iële
    -0.50
    SBATCH
    -0.49
    essä
    -0.48
     الدولى
    -0.47
    ismet
    -0.47
    ashvili
    -0.46
    quehanna
    -0.46
    colate
    -0.45
    POSITIVE LOGITS
     knowledge
    2.55
    knowledge
    2.26
     Knowledge
    2.13
    Knowledge
    2.10
     KNOWLEDGE
    1.98
     conocimiento
    1.68
     connaissances
    1.67
     knowled
    1.66
     conhecimento
    1.62
     conocimientos
    1.61
    Activations Density 0.314%

    No Known Activations