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

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-16K
    11. 14647
    Prev
    Next
    INDEX
    Explanations

    phrases indicating eligibility or options for discounts and assistance in a customer service context

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

    Beginning of sentences

    np_acts-logits-general · gemini-2.0-flash

    phrases like "due to" or "able to"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.58
     noastră
    -0.53
     ✓
    -0.49
     –
    -0.48
     bộ
    -0.45
    ább
    -0.44
     encontrarás
    -0.43
    tvguidetime
    -0.41
    〗
    -0.40
    ʼ
    -0.40
    POSITIVE LOGITS
    StoreMessageInfo
    0.89
     Connectez
    0.81
    enumi
    0.75
    FormTagHelper
    0.75
    }\\
    0.74
    ↵↵↵
    0.70
    ValueStyle
    0.69
     بيها
    0.69
    KeySpec
    0.68
    \}\\
    0.68
    Activations Density 0.082%

    No Known Activations