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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 5042
    Prev
    Next
    INDEX
    Explanations

    financial and economic terms related to transactions and costs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.65
    stdc
    -0.58
    出版年
    -0.58
    feinander
    -0.58
    شهاد
    -0.56
    UnusedPrivate
    -0.52
    TabIndex
    -0.52
     perpetuity
    -0.51
    harusnya
    -0.51
    MergeFrom
    -0.51
    POSITIVE LOGITS
     slightly
    2.13
     slight
    1.94
    slightly
    1.91
     sedikit
    1.87
     briefly
    1.86
     Slightly
    1.80
     quelques
    1.80
     somewhat
    1.74
     some
    1.71
    Slightly
    1.70
    Activations Density 1.035%

    No Known Activations