© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 1610
    Prev
    Next
    INDEX
    Explanations

    phrases indicating roles, agreements, and complex relationships in various contexts

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

    adverbs describing the manner or status of how something is currently being done or exists.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     TextAppearance
    -0.59
     समीक्षक
    -0.56
    LabelTagHelper
    -0.55
    utilisons
    -0.46
     sanitarias
    -0.45
     चीज़ों
    -0.45
    orteur
    -0.41
    InsertCommand
    -0.41
    ApiModelProperty
    -0.40
    __':
    
    -0.39
    POSITIVE LOGITS
     occupied
    1.23
     enjoyed
    1.15
     owned
    1.02
     inhabited
    1.00
     frequented
    0.94
     attended
    0.89
     possessed
    0.88
     wielded
    0.87
     worn
    0.84
    occupied
    0.83
    Activations Density 0.821%

    No Known Activations