© 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. 24-GEMMASCOPE-RES-16K
    11. 6760
    Prev
    Next
    INDEX
    Explanations

    instances of the word "as" used in various contexts, indicating comparisons or conditions

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

    "as" followed by another word

    np_acts-logits-general · gemini-2.0-flash

    as a / as if / as well as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    こと
    -0.52
    able
    -0.46
    いる
    -0.46
     and
    -0.45
    i
    -0.43
    言葉
    -0.43
    нцип
    -0.42
    ,
    -0.41
    ことから
    -0.41
    eliness
    -0.41
    POSITIVE LOGITS
     follows
    1.17
    pires
    1.13
     well
    1.09
     part
    1.08
     opposed
    1.08
     soon
    0.98
    follows
    0.98
    kew
    0.95
    cribes
    0.92
     onderdeel
    0.89
    Activations Density 0.323%

    No Known Activations