Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8415
    Prev
    Next
    INDEX
    Explanations

    the presence of the letter 's' in various contexts, particularly as a plural or possessive marker

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.61
    ตล
    -0.60
    nanoTime
    -0.59
    baguna
    -0.56
    ClientRect
    -0.56
    PRNewswire
    -0.55
     OMITBAD
    -0.55
     behavior
    -0.55
     behaviors
    -0.54
     defStyleAttr
    -0.52
    POSITIVE LOGITS
    s
    0.96
    WriteBarrier
    0.57
    تقاوى
    0.57
     Савезне
    0.55
    檚
    0.54
    Diwedd
    0.52
    setVerticalGroup
    0.52
     papyrus
    0.51
     CreateTagHelper
    0.51
     Stowe
    0.51
    Activations Density 0.157%

    No Known Activations