© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 7351
    Prev
    Next
    INDEX
    Explanations

    references to interactive elements or components in a digital interface, particularly dropdown menus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     دیکھیے
    -0.49
    AreEqual
    -0.49
    antMatchers
    -0.48
     utafitiHapana
    -0.47
    RoutingModule
    -0.47
     AssemblyVersion
    -0.46
    RestController
    -0.46
    HasAnnotation
    -0.46
    OURCE
    -0.46
      [
    -0.45
    POSITIVE LOGITS
    WriteBarrier
    0.78
     elaboration
    0.64
     صوتيه
    0.63
     laby
    0.59
    Endless
    0.59
     تانيه
    0.59
    principalTable
    0.58
     Endless
    0.58
    Autoritní
    0.57
     Roskov
    0.56
    Activations Density 0.310%

    No Known Activations