© 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. 12086
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and political actions, especially sanctions and implications of law

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

    phrases indicating factual assertions or conclusions with supporting evidence or reasoning.

    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
    Teams
    -0.61
    Groups
    -0.59
    Lists
    -0.56
    States
    -0.56
    LISTS
    -0.55
    Accounts
    -0.53
    Departments
    -0.52
    Trips
    -0.52
    Sites
    -0.51
    Reports
    -0.51
    POSITIVE LOGITS
     those
    0.78
    those
    0.73
     dieselben
    0.71
     những
    0.70
     these
    0.69
     mga
    0.66
    那些
    0.64
     Those
    0.64
     thofe
    0.64
    Those
    0.64
    Activations Density 1.254%

    No Known Activations