© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 353
    Prev
    Next
    INDEX
    Explanations

    references to RDF (Resource Description Framework) data structures and formats

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

    Follows "import", rdf, or GO

    np_acts-logits-general · gemini-2.0-flash

    RDF, ontology, semantic web

    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
     barracks
    -0.52
    THISDAY
    -0.50
     schlaf
    -0.50
    SerializedSize
    -0.49
    /*
    -0.48
    tagHelperRunner
    -0.48
     estimés
    -0.47
    gnore
    -0.47
    зможно
    -0.47
    couragement
    -0.47
    POSITIVE LOGITS
     RDF
    0.82
     ontology
    0.79
    rdf
    0.77
     triples
    0.70
    RDF
    0.69
     Ontology
    0.69
     rdf
    0.68
     OWL
    0.64
    ontology
    0.64
     Semantic
    0.64
    Activations Density 0.553%

    No Known Activations