© 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. 40-GEMMASCOPE-RES-16K
    11. 1783
    Prev
    Next
    INDEX
    Explanations

    instances of the word "there" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ContentAlignment
    -0.57
     nonUne
    -0.57
     querían
    -0.45
    demás
    -0.44
    NameInMap
    -0.43
    themselves
    -0.43
    GeneratedMessage
    -0.42
     themselves
    -0.42
    RectangleBorder
    -0.41
     sobie
    -0.41
    POSITIVE LOGITS
     are
    0.71
     tends
    0.50
     tend
    0.48
     exist
    0.46
     plein
    0.46
    eare
    0.46
     includes
    0.45
     seem
    0.44
     isn
    0.41
     happen
    0.41
    Activations Density 0.153%

    No Known Activations