© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5935
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and their patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Spoljašnje
    -0.57
    Produzione
    -0.53
    rigated
    -0.52
    भाव
    -0.50
    farwyddwr
    -0.50
    animity
    -0.47
    bukkit
    -0.47
    aged
    -0.46
    enschein
    -0.46
    škas
    -0.46
    POSITIVE LOGITS
    tanleria
    0.75
    didSet
    0.66
    CloseOperation
    0.64
    msgTypes
    0.62
    iastes
    0.61
    endphp
    0.59
    LabelTagHelper
    0.58
     '\\;'
    0.58
     onCancelled
    0.57
    URIComponent
    0.56
    Activations Density 0.499%

    No Known Activations