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. 8-GEMMASCOPE-RES-16K
    6. 15089
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "mathrm" followed by a numeric value or relevant variable in mathematical or scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estimés
    -1.16
    AsUp
    -1.10
    windowFixed
    -0.93
    endpush
    -0.86
    脚注の使い方
    -0.85
     ApiException
    -0.83
    +"/"+
    -0.82
     Guna
    -0.81
     Völ
    -0.80
    testcase
    -0.80
    POSITIVE LOGITS
    mathrm
    1.76
    setcounter
    0.65
    mathbf
    0.65
     myö
    0.63
    \{\\
    0.60
     ⚫
    0.58
    ⚫
    0.58
     pneum
    0.56
    _
    
    0.55
    𝐳
    0.54
    Activations Density 0.021%

    No Known Activations