© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 30063
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to financial transactions and investments

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

    per cent cited debt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     metabol
    -0.54
     decryption
    -0.51
    twimg
    -0.49
    Vader
    -0.49
    cloudflare
    -0.48
    HtmlAttribute
    -0.48
     wra
    -0.47
    mentaux
    -0.47
    LoadScene
    -0.47
    twilight
    -0.47
    POSITIVE LOGITS
     propOrder
    0.68
    ništ
    0.65
    Халык
    0.60
    INCREF
    0.60
    csol
    0.59
     recommending
    0.56
    GOTREF
    0.55
     endorsement
    0.55
     invokingState
    0.55
     mention
    0.54
    Activations Density 0.471%

    No Known Activations