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

    Neuronpedia

    Jacobian LensNEW
    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. 13086
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" and related terms in various contexts

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

    "the" followed by various common words

    np_acts-logits-general · gemini-2.0-flash

    all the

    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
     two
    -0.60
    Two
    -0.54
     Two
    -0.54
     hombros
    -0.53
    <
    -0.53
     each
    -0.47
    u
    -0.46
    Not
    -0.45
     dois
    -0.45
     двух
    -0.45
    POSITIVE LOGITS
     Wikimedijinoj
    1.02
     Roskov
    1.00
    writeFieldEnd
    0.99
     continúas
    0.93
     $_"
    0.92
     betweenstory
    0.90
    ^(@)
    0.89
     myſelf
    0.88
    enumii
    0.88
     >=",
    0.87
    Activations Density 0.134%

    No Known Activations