© 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. 15391
    Prev
    Next
    INDEX
    Explanations

    phrases that express the concept of options or alternatives involving "one," "two," "day," "week," "year," or "story."

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

    "or" followed by a number

    np_acts-logits-general · gemini-2.0-flash

    or two or so

    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
    
    -0.68
    DataPropertyName
    -0.62
    ="@+
    -0.60
     equal
    -0.59
    andrea
    -0.58
     iprot
    -0.56
    <tfoot>
    -0.56
    metz
    -0.55
    KommentareTeilen
    -0.53
    στό
    -0.51
    POSITIVE LOGITS
     two
    1.41
    two
    1.28
     deux
    1.17
    Two
    1.08
     TWO
    1.03
     Two
    1.03
     zwei
    1.00
    TWO
    0.92
     δύο
    0.91
     duas
    0.89
    Activations Density 0.064%

    No Known Activations