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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 11460
    Prev
    Next
    INDEX
    Explanations

    function calls related to event handling and various library resource loading

    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
    DebuggerNonUser
    -0.76
    tagHelperRunner
    -0.70
    SequentialGroup
    -0.70
    ArgsConstructor
    -0.63
     Roskov
    -0.61
     تكبرها
    -0.58
     Schwier
    -0.58
    gti
    -0.57
    ]++;
    -0.54
     متعلقه
    -0.54
    POSITIVE LOGITS
    makeText
    1.57
    backgroundColor
    1.05
    addCriterion
    0.99
    addEventListener
    0.96
     backgroundColor
    0.91
    styleUrls
    0.80
    Kaynakça
    0.78
    expandindo
    0.74
    ArrowToggle
    0.67
    CppMethod
    0.66
    Activations Density 0.014%

    No Known Activations