© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 1327
    Prev
    Next
    INDEX
    Explanations

    technical terms and specifications related to scientific and engineering contexts

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

    scientific or technical content that contains conjunctions, especially "and/or" in specialized text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    words and tokens that appear in lists or enumerations, particularly those associated with numerical sequences, chemical structures, and technical specifications.

    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
    AddTagHelper
    -0.52
    setAccessible
    -0.52
    MessageTagHelper
    -0.52
    LabelTagHelper
    -0.51
    OCCURRED
    -0.50
    TypedDataSet
    -0.48
    ropshire
    -0.48
    
    -0.48
     سكانية
    -0.47
     propOrder
    -0.47
    POSITIVE LOGITS
     multi
    2.09
    multi
    1.80
     Multi
    1.67
    Multi
    1.65
     dual
    1.64
     MULTI
    1.59
     double
    1.54
    MULTI
    1.48
     multic
    1.37
     multiple
    1.36
    Activations Density 1.389%

    No Known Activations