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. 14-GEMMASCOPE-RES-16K
    6. 4308
    Prev
    Next
    INDEX
    Explanations

    elements related to Spring framework dependency injection and configuration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ölker
    -0.65
    DrawerToggle
    -0.55
    CodeAttribute
    -0.51
     overlay
    -0.50
     Charming
    -0.49
    målet
    -0.49
    overlay
    -0.49
     McGovern
    -0.48
     Schengen
    -0.48
    }))
    
    -0.47
    POSITIVE LOGITS
    ftagPool
    0.76
    MLLoader
    0.76
    ArgsConstructor
    0.69
    fjspx
    0.63
    WithIOException
    0.62
     nahilalakip
    0.62
    stateProvider
    0.61
     phụ
    0.59
     rospy
    0.59
     getService
    0.59
    Activations Density 0.150%

    No Known Activations