© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 352
    Prev
    Next
    INDEX
    Explanations

    references to significant achievements and contributions in a cultural or artistic context

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

    along, among, list of, of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Бахар
    -0.61
     utafitiHapana
    -0.56
     propOrder
    -0.52
    PullParser
    -0.51
    BackPressed
    -0.50
     viață
    -0.49
    MemoryWarning
    -0.48
     invokingState
    -0.47
     HttpServlet
    -0.47
    ViewFeatures
    -0.45
    POSITIVE LOGITS
     along
    0.59
    along
    0.59
     Along
    0.52
     ALONG
    0.50
    Along
    0.48
     наря
    0.45
     among
    0.44
    among
    0.42
     second
    0.41
     Bischof
    0.41
    Activations Density 0.043%

    No Known Activations