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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11337
    Prev
    Next
    INDEX
    Explanations

    references to Android UI components and layout elements

    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
    ThroughAttribute
    -0.99
    XmlEnum
    -0.86
     /\.(
    -0.86
     ostavi
    -0.85
     <=",
    -0.83
    AddTagHelper
    -0.82
    stylers
    -0.79
    ArgsConstructor
    -0.79
    Revenir
    -0.77
    WriteTagHelper
    -0.77
    POSITIVE LOGITS
     GameObject
    0.68
     ElementRef
    0.65
     initWithFrame
    0.58
     ViewGroup
    0.56
    crollView
    0.51
    GameObject
    0.51
     UIView
    0.51
     ReactDOM
    0.49
     container
    0.47
     devices
    0.47
    Activations Density 0.146%

    No Known Activations