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. 16-GEMMASCOPE-RES-16K
    6. 7212
    Prev
    Next
    INDEX
    Explanations

    elements related to health, particularly environmental health and dietary factors

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

    ending in "ing" (gerunds)

    np_acts-logits-general · gemini-2.0-flash

    body, accompaniment, drug, technology, effector, hub, disease

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.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
    ForRow
    -0.56
    databinding
    -0.53
    IntoConstraints
    -0.49
    __(/*!
    -0.48
     racks
    -0.46
    orcid
    -0.46
     ostavi
    -0.45
    loat
    -0.45
    GARD
    -0.44
     primas
    -0.44
    POSITIVE LOGITS
     affair
    0.61
     StatelessWidget
    0.59
    spender
    0.59
    AsUp
    0.57
     createState
    0.57
    之所
    0.57
     conduit
    0.56
    WaitGroup
    0.56
    ApplicationTests
    0.55
     invokingState
    0.55
    Activations Density 0.456%

    No Known Activations