© 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. 9380
    Prev
    Next
    INDEX
    Explanations

    phrases related to customer service in business contexts

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

    Consultation or estimation contexts

    np_acts-logits-general · gemini-2.0-flash

    pricing and consultation

    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
    LookAnd
    -0.62
     Vikipedi
    -0.60
    Autoritní
    -0.59
    richTextPanel
    -0.58
     betweenstory
    -0.57
     resourceCulture
    -0.56
    帖最后由
    -0.54
    uega
    -0.54
     jScrollPane
    -0.52
    verwijspagina
    -0.52
    POSITIVE LOGITS
     estimate
    0.81
     discuss
    0.80
     consultation
    0.79
     presupuesto
    0.77
     Estimate
    0.74
     discussing
    0.73
     explaining
    0.73
     explanations
    0.72
     explanation
    0.71
     estimates
    0.71
    Activations Density 0.182%

    No Known Activations