© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3338
    Prev
    Next
    INDEX
    Explanations

    narrative-driven interactions involving personal experiences and relationships

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

    Interactions, conversations, or encounters with people

    np_acts-logits-general · gemini-2.0-flash

    people walking on sidewalks

    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
    
    -0.56
    enschappelijke
    -0.50
     internal
    -0.49
     sommeil
    -0.48
    Internal
    -0.48
     referrerpolicy
    -0.47
    гиоз
    -0.47
    prodi
    -0.46
     implode
    -0.46
    orney
    -0.46
    POSITIVE LOGITS
     passers
    1.37
     sidewalk
    1.07
     pedestrians
    1.03
     passer
    1.02
     strangers
    1.01
     street
    0.95
     stranger
    0.93
     overheard
    0.92
     strolling
    0.89
     walking
    0.87
    Activations Density 0.326%

    No Known Activations