© 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. 24-GEMMASCOPE-RES-16K
    11. 13863
    Prev
    Next
    INDEX
    Explanations

    references to quantities or numerical data

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

    Numbers less than or equal to ten

    np_acts-logits-general · gemini-2.0-flash

    numerical quantities

    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
    Hauptartikel
    -1.02
    Tikang
    -0.94
     Roskov
    -0.94
     noDo
    -0.91
    Datuak
    -0.90
     estimés
    -0.90
     оригіналу
    -0.88
     ivelany
    -0.87
    SourceChecksum
    -0.87
     transfieras
    -0.87
    POSITIVE LOGITS
    five
    0.75
    eight
    0.65
    four
    0.65
    nine
    0.62
    seven
    0.60
    six
    0.59
    three
    0.56
     six
    0.56
    Five
    0.56
    Four
    0.55
    Activations Density 0.202%

    No Known Activations