© 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. 4-GEMMASCOPE-RES-16K
    11. 15654
    Prev
    Next
    INDEX
    Explanations

    terms related to incorporation or embedding within contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ([]);
    -0.54
    izr
    -0.53
     []).
    -0.52
     attre
    -0.49
    endregion
    -0.48
     Stuhl
    -0.48
    Kole
    -0.48
    AndroidJUnit
    -0.47
     serviced
    -0.47
    emptyset
    -0.46
    POSITIVE LOGITS
     incorporation
    1.42
     incorporated
    1.40
     Incorporation
    1.36
     Incorpor
    1.35
     incorporate
    1.35
     embed
    1.32
     incorporating
    1.28
     incorpor
    1.28
     embedded
    1.27
     incorporates
    1.22
    Activations Density 0.676%

    No Known Activations