© 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. 13192
    Prev
    Next
    INDEX
    Explanations

    references to specific scientific studies or data sources

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

    abbreviations and initialisms, particularly those representing institutional names, chemical compounds, or organizational acronyms.

    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
     bewer
    -0.31
    дцать
    -0.31
    nościo
    -0.30
     Sahne
    -0.30
     địa
    -0.30
     /\.
    -0.29
    Amicalement
    -0.29
     Kammer
    -0.29
     zau
    -0.29
    頃は
    -0.29
    POSITIVE LOGITS
    GEBURTSDATUM
    0.81
    
    0.81
    UnusedPrivate
    0.68
    yntaxException
    0.66
    AISSEE
    0.64
     SwitchCompat
    0.62
     pinulongan
    0.62
     continúas
    0.61
     U
    0.60
     uLocal
    0.60
    Activations Density 1.253%

    No Known Activations