© 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. 3337
    Prev
    Next
    INDEX
    Explanations

    instances of traffic incidents or dangerous driving behavior

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

    Roads, lanes, or paths

    np_acts-logits-general · gemini-2.0-flash

    wrong lane

    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
    tagHelperRunner
    -0.76
    ]")]
    -0.61
    AndEndTag
    -0.56
    LLocation
    -0.55
    :"-"`
    -0.53
     pore
    -0.53
    èdia
    -0.53
    Demografie
    -0.52
     degradability
    -0.51
    entgen
    -0.51
    POSITIVE LOGITS
     lanes
    1.01
     lane
    0.99
     median
    0.73
     sidewalk
    0.70
    Lane
    0.70
     LANE
    0.70
     Lane
    0.69
     Lanes
    0.69
    lane
    0.66
    streifen
    0.63
    Activations Density 0.151%

    No Known Activations