© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 11624
    Prev
    Next
    INDEX
    Explanations

    instances of security, entry, and admission related terms

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

    phrases related to restricted access, entry requirements, or barriers to entering a location or space.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.47
    nonatomic
    -0.45
    UserScript
    -0.42
     odkazy
    -0.42
    outState
    -0.39
     старости
    -0.38
    mobileqq
    -0.38
     lont
    -0.36
     MainAxisSize
    -0.36
     indisponible
    -0.36
    POSITIVE LOGITS
     entry
    2.23
     entering
    2.13
     entrance
    2.02
     enters
    1.95
     Entry
    1.95
     entered
    1.94
    entry
    1.86
     Entering
    1.84
     ENTRY
    1.81
     enter
    1.80
    Activations Density 0.551%

    No Known Activations