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. 4-GEMMASCOPE-RES-16K
    6. 15862
    Prev
    Next
    INDEX
    Explanations

    programming elements related to Android activity lifecycles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     can
    -0.54
     che
    -0.52
     "
    -0.52
     :
    -0.50
     var
    -0.49
     chat
    -0.49
    ↵↵
    -0.49
     **
    -0.49
     qui
    -0.47
     is
    -0.47
    POSITIVE LOGITS
    addCriterion
    2.51
     OnInit
    1.44
    cshtml
    1.38
     HttpNotFound
    1.24
    InstanceState
    1.23
    
    1.14
     myſelf
    1.11
    WireFormatLite
    1.11
    PerformLayout
    1.10
    NgModule
    1.09
    Activations Density 0.010%

    No Known Activations