© 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. 23-GEMMASCOPE-RES-16K
    11. 1722
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fall" and its variations, often in contexts related to emotional states or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entityManager
    -0.63
     DbType
    -0.60
     Vla
    -0.56
    initComponents
    -0.56
     VIAF
    -0.56
     AssemblyTitle
    -0.54
    ilever
    -0.52
     confr
    -0.51
     Enzy
    -0.51
    Wit
    -0.51
    POSITIVE LOGITS
     Fall
    0.88
     fall
    0.85
    Fall
    0.84
     FALL
    0.82
    fall
    0.79
     fell
    0.76
     Fallon
    0.70
     Fell
    0.67
     caída
    0.66
     falling
    0.66
    Activations Density 0.138%

    No Known Activations