© 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. 3793
    Prev
    Next
    INDEX
    Explanations

    elements related to personnel and human resources in formal contexts

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

    punctuation marks, particularly commas and periods that follow or precede other tokens.

    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
     weird
    -0.52
     freaking
    -0.51
     freaked
    -0.48
     goofy
    -0.48
     messy
    -0.47
     subtly
    -0.47
     funny
    -0.47
     gorgeous
    -0.46
     awkward
    -0.46
     freakin
    -0.46
    POSITIVE LOGITS
     Infórmanos
    0.87
     ſche
    0.82
     Governance
    0.79
     organisational
    0.79
     stakeholders
    0.78
     auffi
    0.78
     ſind
    0.77
    ſelf
    0.77
    ſelves
    0.76
     financing
    0.75
    Activations Density 0.645%

    No Known Activations