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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5-GEMMASCOPE-RES-16K
    6. 11076
    Prev
    Next
    INDEX
    Explanations

    terms related to discrimination and its technical aspects in legal and programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hochspringen
    -0.67
    MathML
    -0.63
    ImageContext
    -0.62
     мәкал
    -0.61
    tale
    -0.58
    boat
    -0.58
     Cyn
    -0.58
    <>("
    -0.58
     Pinn
    -0.57
    OGND
    -0.57
    POSITIVE LOGITS
    jLabel
    3.53
     jLabel
    2.17
    jButton
    1.15
    jScrollPane
    1.00
    jPanel
    0.96
    jTextField
    0.88
    iParam
    0.86
     jTextField
    0.83
    initComponents
    0.80
    MessageTagHelper
    0.78
    Activations Density 0.024%

    No Known Activations