© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 39494
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "flavor" or "flavours" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    flavor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     başına
    -0.49
    OneToMany
    -0.49
     post
    -0.48
     Net
    -0.48
     Ponte
    -0.47
     Settembre
    -0.47
    /:
    -0.45
     net
    -0.44
    jke
    -0.44
     Monk
    -0.44
    POSITIVE LOGITS
     Flavor
    1.17
    Flavor
    1.13
     flavor
    1.10
    flavor
    1.02
     flavour
    1.01
     flavors
    0.98
     Flav
    0.94
    Flav
    0.94
     flavored
    0.93
     flavours
    0.89
    Activations Density 0.002%

    No Known Activations