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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15228
    Prev
    Next
    INDEX
    Explanations

    references to authors, researchers, and academic institutions in scientific contexts

    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
    /**
    -0.79
    bootstrapcdn
    -0.79
     propOrder
    -0.73
    complexContent
    -0.73
    etzal
    -0.71
    LabelTagHelper
    -0.69
     noDo
    -0.67
    SourceChecksum
    -0.67
     glyphicon
    -0.67
    ViewImports
    -0.67
    POSITIVE LOGITS
     Aces
    0.88
     Amat
    0.86
     APD
    0.84
     Aps
    0.82
     Ashford
    0.81
     különböz
    0.79
     apes
    0.79
     AttributeSet
    0.78
     Acorn
    0.78
     Arundel
    0.77
    Activations Density 3.616%

    No Known Activations