© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 21205
    Prev
    Next
    INDEX
    Explanations

    mentions of immunohistochemistry and related cellular activities in a scientific context

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

    localized to specific locations

    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
     informée
    -0.50
    parsedMessage
    -0.49
    ParallelGroup
    -0.48
    دانشنامهٔ
    -0.43
    ItemBackground
    -0.43
    OGND
    -0.43
    AccessorTable
    -0.43
     autorytatywna
    -0.42
    numerusform
    -0.41
    HasForeignKey
    -0.40
    POSITIVE LOGITS
     localisation
    0.85
     localization
    0.85
     localización
    0.79
     locations
    0.77
     localização
    0.76
     Localization
    0.76
     Verteilung
    0.75
     LOCATIONS
    0.74
     location
    0.73
     staining
    0.72
    Activations Density 0.467%

    No Known Activations