© 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. 16-GEMMASCOPE-RES-16K
    11. 3733
    Prev
    Next
    INDEX
    Explanations

    references to the presence of items or features in a context

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

    "contain" or "contains"

    np_acts-logits-general · gemini-2.0-flash

    the verb contain

    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
     houſe
    -0.78
     Orville
    -0.75
    )‏
    -0.68
     @"";
    -0.64
     pleaſure
    -0.64
    AddTagHelper
    -0.63
    ModelBuilder
    -0.62
    lück
    -0.61
    SuccessListener
    -0.61
     tymp
    -0.61
    POSITIVE LOGITS
     contains
    1.20
     Contain
    1.20
     contain
    1.16
     CONTAIN
    1.13
     Contains
    1.13
     contained
    1.09
     enthalten
    1.07
    contains
    1.01
    Contain
    0.99
    contain
    0.96
    Activations Density 0.154%

    No Known Activations