© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 11024
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate comparison and evidence between different entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ostavi
    -0.73
    DataMember
    -0.56
    bewerken
    -0.56
    queryInterface
    -0.54
     Biôgrafia
    -0.48
    DebuggerNonUser
    -0.48
    MutableLiveData
    -0.47
     برخ
    -0.45
     démocratie
    -0.43
    hrter
    -0.43
    POSITIVE LOGITS
    الحياه
    0.73
    ngrx
    0.67
    出版年
    0.61
    $_['
    0.60
    '){
    
    0.59
     فريبيس
    0.59
    )]{
    0.59
    ANTLR
    0.58
     configureStore
    0.58
    apimachinery
    0.57
    Activations Density 0.717%

    No Known Activations