© 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. 18-GEMMASCOPE-RES-16K
    11. 6194
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific numerical values and conditions related to health and safety

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

    Tokens after specific words or abbreviations

    np_acts-logits-general · gemini-2.0-flash

    inspecting and troubleshooting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     structuring
    -0.60
     estimés
    -0.59
    atase
    -0.57
     biotechnology
    -0.56
     equestrian
    -0.54
    THON
    -0.54
     sculpt
    -0.53
     servers
    -0.53
     osteoporosis
    -0.52
     neceff
    -0.52
    POSITIVE LOGITS
    MigrationBuilder
    0.80
     suspected
    0.78
     troubleshooting
    0.70
     diagnose
    0.70
     suspect
    0.69
     Diagnose
    0.69
     inspection
    0.69
     INSPECTION
    0.68
     Inspection
    0.68
     troubleshoot
    0.66
    Activations Density 0.171%

    No Known Activations