© 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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7959
    Prev
    Next
    INDEX
    Explanations

    mentions of meals and dining experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    psons
    -0.55
    PerformLayout
    -0.54
    __).
    -0.48
    chaff
    -0.45
     Measure
    -0.44
    erval
    -0.43
    dise
    -0.43
    ]));
    -0.43
     sper
    -0.42
     Dodson
    -0.42
    POSITIVE LOGITS
    time
    0.77
    mybatisplus
    0.73
     Escolar
    0.71
     Poitiers
    0.65
    TIME
    0.65
     CreateTagHelper
    0.64
     pail
    0.63
     MatDialog
    0.62
     onCreateView
    0.62
     ItemStack
    0.61
    Activations Density 0.048%

    No Known Activations