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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-GEMMASCOPE-RES-16K
    6. 7926
    Prev
    Next
    INDEX
    Explanations

    sequence indicators and numerical data in technical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    indler
    -0.56
    gula
    -0.54
     zw
    -0.54
     kal
    -0.48
    jon
    -0.48
    Ernie
    -0.48
     đ
    -0.47
    RefNanny
    -0.47
     Sein
    -0.47
    hiza
    -0.47
    POSITIVE LOGITS
    subsubsection
    1.15
    subsection
    1.02
    +#+#
    0.90
    المناصب
    0.88
     itſelf
    0.86
    tableFuture
    0.83
    ftagPool
    0.81
     myſelf
    0.80
     الرياضيه
    0.79
    PyExc
    0.77
    Activations Density 0.378%

    No Known Activations