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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 5611
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate instructions or reminders involving the word "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Мексичка
    -0.69
     PicClick
    -0.55
    koła
    -0.55
    gadier
    -0.55
    FieldNumber
    -0.54
    νω
    -0.54
     getResources
    -0.53
    <<<<<<<<
    -0.53
     indis
    -0.52
     newBuilder
    -0.52
    POSITIVE LOGITS
     обязательно
    0.69
    记得
    0.67
     mentioning
    0.66
    usermodel
    0.65
     đừng
    0.64
     culturelles
    0.64
     vocales
    0.63
     mention
    0.61
     EconPapers
    0.60
    бяза
    0.60
    Activations Density 0.065%

    No Known Activations