© 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. 13-GEMMASCOPE-RES-16K
    11. 8040
    Prev
    Next
    INDEX
    Explanations

    patterns related to the usage and formatting of delimiters, specifically commas and semicolons, in programming or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bì
    -0.57
    <u>
    -0.55
    RIP
    -0.53
    bu
    -0.49
     bid
    -0.49
     preprint
    -0.49
    kins
    -0.48
    험
    -0.48
    enberg
    -0.48
     deep
    -0.48
    POSITIVE LOGITS
    MessageTagHelper
    0.86
    StructEnd
    0.84
    yntaxException
    0.83
    CloseOperation
    0.82
     AssemblyCulture
    0.81
     commas
    0.78
    RetentionPolicy
    0.74
     betweenstory
    0.72
     الحره
    0.70
     ErrIntOverflow
    0.70
    Activations Density 0.279%

    No Known Activations