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. 15-GEMMASCOPE-RES-16K
    6. 8812
    Prev
    Next
    INDEX
    Explanations

    concepts related to nursing leadership and family diversity issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Suffer
    -0.65
     Amateur
    -0.58
     pensioners
    -0.58
     salesmen
    -0.57
     Breeding
    -0.56
     sarcas
    -0.56
     bloodshed
    -0.55
     Manufacturers
    -0.55
     sternly
    -0.55
    僕
    -0.55
    POSITIVE LOGITS
    :✨
    0.72
     interventions
    0.64
     continuum
    0.61
    bootstrapcdn
    0.60
    AndEndTag
    0.59
     behaviors
    0.58
    SequentialGroup
    0.57
     person
    0.57
    DidLoad
    0.57
    transQ
    0.57
    Activations Density 1.457%

    No Known Activations