© 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. 11619
    Prev
    Next
    INDEX
    Explanations

    instances of calls to action, particularly related to reading or exploring further content

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

    "Read More" links and related clickbait-style content navigation elements.

    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
    Chham
    -0.64
     الرياضيه
    -0.62
    autoreleasepool
    -0.59
     fieldNum
    -0.54
    ModelAdmin
    -0.52
    oneofs
    -0.52
    EndGlobalSection
    -0.51
     jsPsych
    -0.51
     click
    -0.50
    ConstraintMaker
    -0.50
    POSITIVE LOGITS
    setVerticalGroup
    0.57
     penuh
    0.40
     líquida
    0.33
    XmlIgnore
    0.33
     Stoffe
    0.33
     Ejecutivo
    0.32
     całość
    0.32
     distribuição
    0.32
     trânsito
    0.32
     posé
    0.31
    Activations Density 0.135%

    No Known Activations