© 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. 7077
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notations involving fractions, variables, and functions

    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
     Fri
    -0.46
    piration
    -0.43
     St
    -0.43
    GeneratedValue
    -0.43
     strtok
    -0.42
     Freitag
    -0.42
    alus
    -0.42
     North
    -0.42
     familiari
    -0.40
    自制
    -0.40
    POSITIVE LOGITS
     autorytatywna
    0.99
     متعلقه
    0.95
     CreateTagHelper
    0.92
    WriteTagHelper
    0.91
     ویکی‌پدی
    0.84
    styleType
    0.84
     pinulongan
    0.82
     NSCoder
    0.82
     propTypes
    0.81
    XmlAccessorType
    0.80
    Activations Density 1.363%

    No Known Activations