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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53001
    Prev
    Next
    INDEX
    Explanations

    terms related to caregiving and support services

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

    food, hygiene, and medical supplies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.65
     FetchType
    -0.57
    setCellStyle
    -0.56
    렷
    -0.54
    Polecam
    -0.52
     perfección
    -0.52
    плуата
    -0.52
     perfeita
    -0.52
    Datuak
    -0.51
     дописавши
    -0.51
    POSITIVE LOGITS
     donated
    0.66
     raffle
    0.56
    LabelTagHelper
    0.55
     HIV
    0.52
    HMIS
    0.52
     counseling
    0.51
     Therapeutic
    0.51
     therapeutic
    0.51
     dignified
    0.51
     pinulongan
    0.51
    Activations Density 0.075%

    No Known Activations