© 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-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 8920
    Prev
    Next
    INDEX
    Explanations

    patterns and sequences related to timing and order in messages or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.53
    مراجع
    -0.51
     ivelany
    -0.50
    KommentareTeilen
    -0.49
    sidemargin
    -0.48
     Paglinawan
    -0.47
    الحياه
    -0.47
     lenker
    -0.47
    rungsseite
    -0.46
    Життєпис
    -0.45
    POSITIVE LOGITS
     next
    0.57
     preceding
    0.54
     preceded
    0.53
     adjacent
    0.52
     consecutive
    0.52
     adjoining
    0.49
     succession
    0.46
     Италијани
    0.46
     preced
    0.46
     sequence
    0.46
    Activations Density 0.899%

    No Known Activations