© 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. 8827
    Prev
    Next
    INDEX
    Explanations

    references to artistic contributions or conceptual frameworks in various contexts

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

    Parentheses and quotation marks

    np_acts-logits-general · gemini-2.0-flash

    Giro d'Italia

    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
     nemici
    -0.90
     stället
    -0.88
     feroit
    -0.84
     popoli
    -0.83
     alberi
    -0.82
     avoient
    -0.82
     dieux
    -0.82
     détru
    -0.81
     enfans
    -0.80
     soldati
    -0.80
    POSITIVE LOGITS
     flames
    0.53
    Portale
    0.51
    vedi
    0.50
    ses
    0.50
    ing
    0.49
    ist
    0.49
     own
    0.48
     Belleville
    0.48
    s
    0.47
     Shakspeare
    0.47
    Activations Density 0.019%

    No Known Activations