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

    Neuronpedia

    Jacobian LensNEW
    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. 6995
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and contexts

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

    numbers and numerical data, particularly phone numbers, currency codes, dates, and numerical identifiers.

    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
     ProtoMessage
    -0.72
    AddTagHelper
    -0.57
     Mexique
    -0.56
    Rüyada
    -0.53
     kasarigan
    -0.52
    AndEndTag
    -0.51
    期刊论文
    -0.49
    calientes
    -0.48
    scriptcase
    -0.48
     Egyptian
    -0.47
    POSITIVE LOGITS
     Georgia
    0.95
     Georgian
    0.91
     GEORGIA
    0.88
    Georgia
    0.84
     Tbilisi
    0.81
     georg
    0.78
     georgia
    0.74
    Georg
    0.70
    georg
    0.67
    ashvili
    0.66
    Activations Density 0.027%

    No Known Activations