© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 5403
    Prev
    Next
    INDEX
    Explanations

    words associated with sweetness or sugary items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     manguera
    -0.42
    chartInstance
    -0.41
    usser
    -0.36
    chufe
    -0.36
    zien
    -0.35
    輻
    -0.35
     copos
    -0.35
     Forster
    -0.34
    льными
    -0.34
     convict
    -0.33
    POSITIVE LOGITS
     sweet
    0.93
    sweet
    0.90
    Sweet
    0.84
     SWEET
    0.83
     Sweet
    0.76
    SWEET
    0.75
     sweeter
    0.65
    hearts
    0.64
     dulce
    0.63
     süß
    0.59
    Activations Density 0.140%

    No Known Activations