© 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. 15-GEMMASCOPE-RES-16K
    6. 1677
    Prev
    Next
    INDEX
    Explanations

    references to embassies and diplomatic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlType
    -0.45
    complexContent
    -0.43
    ppuden
    -0.41
    UnusedPrivate
    -0.40
    MigrationBuilder
    -0.38
    PullParser
    -0.37
    userdetails
    -0.37
    oredCriteria
    -0.37
     <>",
    -0.36
     Cæsar
    -0.36
    POSITIVE LOGITS
     diplomatic
    0.96
     Embassy
    0.90
    ambassade
    0.88
     Diplomatic
    0.87
     embassies
    0.86
     embassy
    0.84
     diplomats
    0.79
     diplomat
    0.77
    Ambassador
    0.77
     Ambassador
    0.75
    Activations Density 0.254%

    No Known Activations