© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12383
    Prev
    Next
    INDEX
    Explanations

    references to investments and funding in the context of business or startups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebServlet
    -0.62
    脚注の使い方
    -0.60
    (!__
    -0.58
     ***!
    -0.56
    __))
    -0.55
     "..\..\
    -0.54
    flink
    -0.53
    rxjs
    -0.53
    dersfield
    -0.53
     "..\..\..\
    -0.52
    POSITIVE LOGITS
     fund
    0.98
     investment
    0.94
     Fund
    0.89
     funds
    0.88
     hedge
    0.85
     investing
    0.84
     investors
    0.84
     Investment
    0.84
    investment
    0.81
    Investment
    0.80
    Activations Density 0.103%

    No Known Activations