© 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. 3995
    Prev
    Next
    INDEX
    Explanations

    phrases related to quality and excellence

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

    the phrase "well-" followed by an adjective (such as "well-known," "well-worth," "well-kept," "well-studied," "well-heeled," "well-covered," "well-positioned," "well-defined").

    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
    transQ
    -0.47
     красота
    -0.41
     béné
    -0.41
    anhänger
    -0.39
     MUNICIPAL
    -0.39
     feier
    -0.39
     belangrij
    -0.38
     luxury
    -0.38
     bæ
    -0.38
    Purity
    -0.38
    POSITIVE LOGITS
     structured
    0.63
     autorytatywna
    0.63
     organized
    0.62
     orchestrated
    0.58
     equipped
    0.57
     balanced
    0.57
     groomed
    0.57
     defined
    0.57
     organised
    0.56
     crafted
    0.56
    Activations Density 0.169%

    No Known Activations