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. 7-GEMMASCOPE-RES-16K
    6. 8841
    Prev
    Next
    INDEX
    Explanations

    conditional statements and control structures in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.78
    出版年
    -0.72
     invokingState
    -0.64
    creativecommons
    -0.64
    Clik
    -0.61
     cellpadding
    -0.56
    AttributeSet
    -0.56
    ----</
    -0.56
    {#
    -0.55
    <tbody>
    -0.55
    POSITIVE LOGITS
     jLabel
    1.18
     iParam
    0.86
     jScrollPane
    0.85
     DriverManager
    0.84
     FileWriter
    0.82
     UnityEngine
    0.81
     &___
    0.79
     ResourceManager
    0.76
    getItem
    0.76
     betweenstory
    0.70
    Activations Density 0.009%

    No Known Activations