© 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. 10-GEMMASCOPE-RES-16K
    11. 15144
    Prev
    Next
    INDEX
    Explanations

    actions and events related to possession and transfer of items, particularly in a legal or contraband context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TintMode
    -0.50
    ContentAsync
    -0.50
    WebControls
    -0.46
    qrstuvwxyz
    -0.41
     MonoBehaviour
    -0.40
    WaitGroup
    -0.40
    CAPIT
    -0.38
     vocation
    -0.38
     Salve
    -0.37
    Referencie
    -0.37
    POSITIVE LOGITS
     confiscated
    0.54
    AsStream
    0.46
     wireType
    0.45
    supplies
    0.45
    removeChild
    0.44
    拿出
    0.44
     confis
    0.44
    用到
    0.43
     copies
    0.43
     gadgets
    0.42
    Activations Density 0.758%

    No Known Activations