© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2435
    Prev
    Next
    INDEX
    Explanations

    phrases indicating sequences of events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.63
     HasFactory
    -0.57
    iciens
    -0.56
    typeorm
    -0.54
    ftagPool
    -0.53
    hdashline
    -0.51
     memutus
    -0.51
    glTexCoord
    -0.50
    asztal
    -0.50
    InputBorder
    -0.50
    POSITIVE LOGITS
     thereafter
    1.13
     Thereafter
    0.98
    Далее
    0.83
    Даль
    0.78
    以降
    0.78
     Далее
    0.77
     subsequent
    0.77
     afterwards
    0.76
     Daarna
    0.75
     afterward
    0.73
    Activations Density 0.495%

    No Known Activations