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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10835
    Prev
    Next
    INDEX
    Explanations

    phrases discussing the quality and potential of care in nursing or healthcare contexts

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

    after "the"

    np_acts-logits-general · gemini-2.0-flash

    specific concept or quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    aarrggbb
    -0.74
    MemoryWarning
    -0.67
    RTLD
    -0.65
    EditorBrowsable
    -0.64
    featureID
    -0.61
     Italijanski
    -0.61
    WriteBarrier
    -0.60
     CascadeType
    -0.59
    RuleContext
    -0.59
    MessageTagHelper
    -0.57
    POSITIVE LOGITS
     physical
    1.29
     technical
    1.22
     actual
    1.22
     selve
    1.18
     practical
    1.12
     substantive
    1.03
    physical
    1.01
     själva
    0.98
     mechanics
    0.98
    technical
    0.97
    Activations Density 0.728%

    No Known Activations