© 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. 1-GEMMASCOPE-RES-16K
    6. 4989
    Prev
    Next
    INDEX
    Explanations

    elements related to user input fields and data management in forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -1.28
    expandindo
    -1.18
     AssemblyCulture
    -1.16
    tagHelperRunner
    -1.15
     وتسجيلات
    -1.13
     חיצוניים
    -1.13
     للمعارف
    -1.10
    httphttps
    -1.10
     StatefulWidget
    -1.05
     الحره
    -1.05
    POSITIVE LOGITS
    *
    0.46
    _
    0.44
     toggle
    0.39
    .
    0.39
    !
    0.38
      
    0.38
     
    0.36
     [
    0.36
     язы
    0.35
    +
    0.35
    Activations Density 0.694%

    No Known Activations