Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 9418
    Prev
    Next
    INDEX
    Explanations

    strings related to financial terms and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uſed
    -0.90
     surla
    -0.88
     houſe
    -0.86
     Jefus
    -0.85
     ―――――
    -0.83
     Houſe
    -0.82
     חיצוניים
    -0.82
     faſt
    -0.81
     Monfieur
    -0.81
     Majefty
    -0.81
    POSITIVE LOGITS
    AppMethodBeat
    0.53
    あら
    0.48
    ...
    0.47
    举
    0.42
     ...
    0.41
    予
    0.40
     ú
    0.40
    舉
    0.38
     έ
    0.38
    bino
    0.38
    Activations Density 0.863%

    No Known Activations