© 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. 2-GEMMASCOPE-RES-16K
    11. 4179
    Prev
    Next
    INDEX
    Explanations

    references to organizations and groups, particularly those related to conservation or military

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Benton
    -0.44
     ContentValues
    -0.43
    idão
    -0.37
     înc
    -0.35
    felizmente
    -0.35
     Mitarbeit
    -0.35
     sentenza
    -0.35
    selaer
    -0.35
     Beschäf
    -0.34
    Dem
    -0.34
    POSITIVE LOGITS
     rag
    0.72
     Corps
    0.72
    Personensuche
    0.65
    Corps
    0.64
     kun
    0.63
     corps
    0.62
     Kun
    0.59
    corps
    0.58
     Corp
    0.57
    sidemargin
    0.57
    Activations Density 0.578%

    No Known Activations