© 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. 14959
    Prev
    Next
    INDEX
    Explanations

    questions about perceptions and evaluations involving individuals or conflicts

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

    preceding a verb "to be" or acting/feeling verbs

    np_acts-logits-general · gemini-2.0-flash

    describes actions or states

    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
     chré
    -0.66
     noires
    -0.66
    entibus
    -0.61
     finnas
    -0.58
     médié
    -0.57
     fermés
    -0.56
     automatiques
    -0.55
     complètes
    -0.54
     Teilnahme
    -0.54
     indépend
    -0.54
    POSITIVE LOGITS
     behave
    1.00
     behaves
    0.95
     behaved
    0.91
     handled
    0.87
     behaving
    0.80
     worded
    0.80
     fared
    0.78
    djangoproject
    0.74
     structured
    0.70
     interact
    0.70
    Activations Density 0.342%

    No Known Activations