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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 9884
    Prev
    Next
    INDEX
    Explanations

    mentions of "Deep State" and related terms or concepts

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

    "deep"

    np_acts-logits-general · gemini-2.0-flash

    deep State

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    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
    -1.02
    djangoproject
    -0.98
    InputBorder
    -0.92
    MessageTagHelper
    -0.89
    ImageContext
    -0.83
    expandindo
    -0.82
    AccessorTable
    -0.82
    цездатний
    -0.82
     ويكيپيديا
    -0.81
    RegistryLite
    -0.79
    POSITIVE LOGITS
     deep
    1.31
     Deep
    1.29
    Deep
    1.27
     DEEP
    1.26
    deep
    1.23
     deeply
    1.17
     deeper
    1.10
    DEEP
    1.09
     deepest
    1.08
     depth
    1.03
    Activations Density 0.081%

    No Known Activations