© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12320
    Prev
    Next
    INDEX
    Explanations

    references to food preparation techniques and ingredient combinations

    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
     defaultstate
    -0.69
    مقاله
    -0.65
     للمعارف
    -0.61
     CreateTagHelper
    -0.61
    তথ্যসূত্র
    -0.61
    Personendaten
    -0.59
    脚注の使い方
    -0.58
    Meanwhile
    -0.58
    complexContent
    -0.58
     simultaneously
    -0.57
    POSITIVE LOGITS
    NameInMap
    0.63
     Brother
    0.56
     upstairs
    0.51
    Sisters
    0.51
    Sister
    0.50
     Sister
    0.49
     smelly
    0.48
    GRP
    0.47
    Brother
    0.47
    Portály
    0.47
    Activations Density 0.038%

    No Known Activations