© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 7263
    Prev
    Next
    INDEX
    Explanations

    terms related to collective experiences or generalization

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

    "All" followed by a category or domain

    np_acts-logits-general · gemini-2.0-flash

    all and following context

    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
     ognuno
    -0.82
     EconPapers
    -0.77
     ciascuno
    -0.76
     genoux
    -0.68
     allemaal
    -0.68
     chacun
    -0.66
     each
    -0.66
     cualquiera
    -0.65
     algunas
    -0.65
     algunos
    -0.64
    POSITIVE LOGITS
     aspects
    1.06
     major
    0.97
     facets
    0.83
     relevant
    0.77
     levels
    0.77
     types
    0.76
     phases
    0.76
    aspects
    0.74
     kecuali
    0.74
     remaining
    0.72
    Activations Density 0.226%

    No Known Activations