Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 1233
    Prev
    Next
    INDEX
    Explanations

    components related to food additives and their effects on health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.68
    InputTagHelper
    -0.66
    setVerticalGroup
    -0.66
    +:+
    -0.60
     Jill
    -0.58
    quelize
    -0.58
     chauffeur
    -0.58
     interpreters
    -0.58
    SharedDtor
    -0.56
     epist
    -0.56
    POSITIVE LOGITS
     added
    0.79
    Contains
    0.76
     Added
    0.72
    contains
    0.72
     artificial
    0.71
    Added
    0.70
     additives
    0.70
     Contains
    0.67
    added
    0.66
    添加
    0.64
    Activations Density 0.405%

    No Known Activations