© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16291
    Prev
    Next
    INDEX
    Explanations

    sections or labels related to code or programming issues, particularly those associated with Common Weakness Enumeration (CWE) identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     result
    -0.32
     balance
    -0.31
     benefit
    -0.31
     colspan
    -0.31
     pass
    -0.29
     Results
    -0.29
    atea
    -0.29
    ผล
    -0.28
     conto
    -0.28
     Hoon
    -0.28
    POSITIVE LOGITS
    :✨
    9.31
     autorytatywna
    1.26
    GEBURTSDATUM
    1.21
     EconPapers
    1.19
    ✨:
    1.19
    Rüyada
    1.10
    SharedCtor
    1.07
     nahilalakip
    1.05
    msgTypes
    1.04
    tanleria
    0.98
    Activations Density 0.004%

    No Known Activations