© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104503
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to specific functions and properties in technical or legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -0.29
     nime
    -0.26
    D
    -0.26
    tungs
    -0.26
     like
    -0.25
    Z
    -0.25
     called
    -0.24
    N
    -0.24
    ...
    -0.24
    ​
    -0.24
    POSITIVE LOGITS
    enderror
    0.99
     NSCoder
    0.92
    Diweddarwch
    0.91
    CloseOperation
    0.85
     estekak
    0.85
     contextLoads
    0.84
     الحره
    0.84
     дописавши
    0.84
    parsedMessage
    0.83
    SpringBootTest
    0.83
    Activations Density 0.109%

    No Known Activations