Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4399
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming or data representation

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

    RDF or ontology-related terms

    np_acts-logits-general · gemini-2.0-flash

    RDF ontology concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.57
    :+:
    -0.56
    +#+
    -0.55
     Stav
    -0.53
     Alvarado
    -0.52
    saraba
    -0.49
    Carriera
    -0.48
     touche
    -0.48
    äule
    -0.47
    kok
    -0.47
    POSITIVE LOGITS
     ontology
    0.90
     triples
    0.84
     concepts
    0.82
     concept
    0.81
     Concept
    0.81
     onto
    0.81
    onto
    0.81
     rdf
    0.79
     RDF
    0.78
     Ont
    0.77
    Activations Density 0.383%

    No Known Activations