© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8163
    Prev
    Next
    INDEX
    Explanations

    phrases indicating assistance or helpfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setPixel
    -0.49
     admitted
    -0.48
     hates
    -0.47
     interviewed
    -0.46
     orec
    -0.45
    Eternal
    -0.45
     rushed
    -0.45
     erythrocytes
    -0.44
     asked
    -0.44
     preguntar
    -0.44
    POSITIVE LOGITS
     helps
    0.86
     kaarangay
    0.81
     Helps
    0.73
    helps
    0.72
     nhằm
    0.69
     ensures
    0.69
    Helps
    0.68
     affords
    0.67
     ivelany
    0.67
     باعث
    0.67
    Activations Density 0.624%

    No Known Activations