© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14772
    Prev
    Next
    INDEX
    Explanations

    financial figures and budget-related information

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

    Following a number or currency value

    np_acts-logits-general · gemini-2.0-flash

    revenue recording and financial amounts

    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
    principalTable
    -0.70
     spä
    -0.65
     nanti
    -0.65
     bientôt
    -0.60
     someday
    -0.58
     später
    -0.58
    Eventually
    -0.55
     rarement
    -0.55
     soon
    -0.54
     Later
    -0.54
    POSITIVE LOGITS
     recorded
    0.95
     recording
    0.92
     stood
    0.90
     registering
    0.80
    recording
    0.79
    stood
    0.76
    recorded
    0.76
     amounted
    0.76
     Recording
    0.74
    findpost
    0.74
    Activations Density 0.180%

    No Known Activations