© 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. 15862
    Prev
    Next
    INDEX
    Explanations

    references to awareness and perception

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

    words describing people who are perceptive or observant.

    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
     onCreateView
    -0.39
    DatabaseError
    -0.35
     arşivlendi
    -0.29
    Nationalité
    -0.28
    appendTo
    -0.28
    preuve
    -0.27
     Empfehlungen
    -0.26
    =======
    -0.25
    ReturnValue
    -0.25
     Investigación
    -0.25
    POSITIVE LOGITS
     notice
    2.78
     noticing
    2.66
     noticed
    2.63
    notice
    2.45
     Notice
    2.38
    Notice
    2.34
     notices
    2.31
    noticed
    2.25
     NOTICE
    1.98
    notices
    1.89
    Activations Density 0.603%

    No Known Activations