© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6906
    Prev
    Next
    INDEX
    Explanations

    references to "deep" concepts or terms, particularly in relation to deep learning, deep state theories, or deep emotional states

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

    "deep"

    np_acts-logits-general · gemini-2.0-flash

    deep State or South

    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
     виправивши
    -1.14
    MessageTagHelper
    -1.10
    цездатний
    -1.00
    djangoproject
    -0.99
    PreferredItem
    -0.98
     MainAxisSize
    -0.96
    OGND
    -0.95
    RegistryLite
    -0.95
    ImageContext
    -0.94
    expandindo
    -0.93
    POSITIVE LOGITS
     deep
    1.15
     Deep
    1.11
    Deep
    1.10
     DEEP
    1.09
    deep
    1.01
    DEEP
    0.88
     deeply
    0.88
     deepest
    0.87
     deeper
    0.84
     rooted
    0.82
    Activations Density 0.069%

    No Known Activations