© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9502
    Prev
    Next
    INDEX
    Explanations

    terms related to UI component styling and layout attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.84
    
    -0.75
    Портал
    -0.75
    DOCTYPE
    -0.74
     متعلقه
    -0.73
     nakalista
    -0.72
     Portail
    -0.71
    pushFollow
    -0.69
     defaultstate
    -0.69
    InjectAttribute
    -0.68
    POSITIVE LOGITS
     ps
    0.96
    Становништво
    0.88
    EntityFramework
    0.83
     Ps
    0.77
    enumi
    0.69
    initComponents
    0.64
     PS
    0.64
    CodeAnalysis
    0.63
    Ps
    0.62
    ps
    0.62
    Activations Density 0.005%

    No Known Activations