© 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. 35-GEMMASCOPE-RES-16K
    11. 7365
    Prev
    Next
    INDEX
    Explanations

    references to international collaboration and coordination in security matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.36
     statewide
    -0.34
    orgung
    -0.34
     ben
    -0.33
    opardy
    -0.33
    væ
    -0.32
    Autoritní
    -0.32
     Mitt
    -0.31
     amare
    -0.31
    ijuana
    -0.31
    POSITIVE LOGITS
     summit
    0.77
     Ministerial
    0.68
     ministerial
    0.66
     Summit
    0.65
     Declaration
    0.63
     plenary
    0.62
    summit
    0.61
     declaration
    0.60
     ministers
    0.59
     summits
    0.58
    Activations Density 0.232%

    No Known Activations