© 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-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6474
    Prev
    Next
    INDEX
    Explanations

    instances of the word "stands" indicating a subject's location or position

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
    WithIOException
    -0.60
    yntax
    -0.53
    Heer
    -0.48
     heapq
    -0.43
    TIP
    -0.43
     Veget
    -0.42
    ﴿
    -0.41
     Италијани
    -0.40
     supre
    -0.40
     Jue
    -0.40
    POSITIVE LOGITS
     stands
    1.52
     lies
    1.45
     belongs
    1.27
     remains
    1.20
     liegt
    1.16
     rests
    1.16
     resides
    1.16
     exists
    1.13
     sits
    1.13
     steht
    1.06
    Activations Density 0.221%

    No Known Activations