© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 9905
    Prev
    Next
    INDEX
    Explanations

    references to specific patients and their medical conditions

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

    arrivals and happenings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EnumMember
    -0.39
     opdracht
    -0.36
     lazos
    -0.35
     malade
    -0.35
     ferdig
    -0.33
     recul
    -0.33
     liné
    -0.33
     læng
    -0.32
     bezig
    -0.32
     bronce
    -0.31
    POSITIVE LOGITS
     arrives
    1.84
     arrive
    1.78
     arrived
    1.74
     arriving
    1.72
     arrival
    1.62
    arrive
    1.49
     Arrive
    1.46
    arrived
    1.41
     came
    1.40
     Arri
    1.39
    Activations Density 0.111%

    No Known Activations