© 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. 5-GEMMASCOPE-RES-16K
    11. 3355
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and structures related to sets and functions

    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
     onAnimation
    -0.94
    PhysRevD
    -0.87
    writeFieldEnd
    -0.73
     newOwner
    -0.70
    DotNetBar
    -0.70
    Tikang
    -0.69
    íncia
    -0.65
    LookAnd
    -0.64
     LoggerFactory
    -0.64
    parsedMessage
    -0.64
    POSITIVE LOGITS
    AddTagHelper
    0.61
    BufferException
    0.50
    AddHtmlAttribute
    0.48
    LocalizedString
    0.48
     között
    0.48
     antichi
    0.45
    abstractmethod
    0.44
    ListAdapter
    0.43
    Nonnull
    0.43
    ributes
    0.43
    Activations Density 0.456%

    No Known Activations