© 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. 24-GEMMASCOPE-RES-16K
    6. 9540
    Prev
    Next
    INDEX
    Explanations

    references to "attorney" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following "att" or "Att"

    np_acts-logits-general · gemini-2.0-flash

    attending, attorney, attributions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.84
    webElementXpaths
    -0.75
    WriteBarrier
    -0.69
     lenker
    -0.65
    MemoryWarning
    -0.61
    IonicModule
    -0.59
     kasarigan
    -0.55
     requestCode
    -0.53
     препратки
    -0.53
    tagext
    -0.52
    POSITIVE LOGITS
     least
    0.59
     Least
    0.56
    tainment
    0.51
    ribut
    0.51
     LEAST
    0.51
    Least
    0.51
    decer
    0.50
     tach
    0.49
     SafeMath
    0.49
    ribu
    0.48
    Activations Density 0.132%

    No Known Activations