© 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. 22-GEMMASCOPE-RES-16K
    11. 10652
    Prev
    Next
    INDEX
    Explanations

    the word "there" and its variations, indicating a focus on locational or existence concepts

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

    "There are"

    np_acts-logits-general · gemini-2.0-flash

    there are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endphp
    -0.60
    resave
    -0.59
    principalColumn
    -0.57
    Geplaatst
    -0.56
    ragalactic
    -0.56
    weth
    -0.55
    stood
    -0.55
    gameserver
    -0.55
    strix
    -0.55
    protoimpl
    -0.54
    POSITIVE LOGITS
     are
    1.64
     were
    1.11
     aren
    0.91
    are
    0.83
     são
    0.82
     weren
    0.82
     sont
    0.80
     zijn
    0.73
     sind
    0.69
     ARE
    0.68
    Activations Density 0.109%

    No Known Activations