© 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. 33-GEMMASCOPE-RES-16K
    11. 11472
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and their significance in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemBackground
    -0.65
    SharedDtor
    -0.65
    .*")]
    -0.64
    parsedMessage
    -0.64
    principalColumn
    -0.62
     otomatig
    -0.61
     Cæsar
    -0.60
     pleaſure
    -0.59
    OGND
    -0.57
    ロウィン
    -0.57
    POSITIVE LOGITS
     department
    0.48
    department
    0.41
     departmental
    0.38
     Department
    0.38
    Department
    0.38
    departments
    0.35
     DEPARTMENT
    0.35
     xo
    0.35
     Departmental
    0.34
     kemajuan
    0.34
    Activations Density 0.187%

    No Known Activations