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. 20-GEMMASCOPE-RES-16K
    6. 15817
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal matters and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "legal"

    np_acts-logits-general · gemini-2.0-flash

    legal contexts and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    IContainer
    -0.87
    initComponents
    -0.69
    ValueStyle
    -0.68
    AddTagHelper
    -0.68
     liners
    -0.62
    fjspx
    -0.62
     <=",
    -0.61
    </thead>
    -0.61
    发表于
    -0.60
    Salta
    -0.59
    POSITIVE LOGITS
    ább
    0.62
     đương
    0.55
    istic
    0.54
    ifolium
    0.52
     tender
    0.49
    ize
    0.49
    iritto
    0.49
    isir
    0.49
    azza
    0.48
     counsel
    0.47
    Activations Density 0.082%

    No Known Activations