© 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. 16-GEMMASCOPE-RES-16K
    11. 1751
    Prev
    Next
    INDEX
    Explanations

    code-related terms and structures, particularly those involving data types and storage options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by a number

    np_acts-logits-general · gemini-2.0-flash

    fixed, sint, uint, sfixed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Adicion
    -0.51
     eccl
    -0.51
     latine
    -0.49
    PROLOG
    -0.48
     Quelles
    -0.48
    ,:)
    -0.48
     Diagrams
    -0.48
    anadas
    -0.47
     coleg
    -0.47
     competitiveness
    -0.47
    POSITIVE LOGITS
    AnchorStyles
    0.86
    MessageTagHelper
    0.72
     חיצוניים
    0.71
    曖昧さ回避
    0.70
    TintMode
    0.68
     estimés
    0.67
    featureID
    0.64
     ujednoznacz
    0.62
    Sucesor
    0.62
    ModelAdmin
    0.61
    Activations Density 0.738%

    No Known Activations