© 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 EvalsExportsinterp-engineNEWAPI 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. 1163
    Prev
    Next
    INDEX
    Explanations

    phrases that use the word "as" to establish comparisons or equivalences

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

    "as" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    defining roles with "as"

    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
    脚注の使い方
    -0.65
     vulgaires
    -0.63
    AndEndTag
    -0.58
     Selected
    -0.57
    ########.
    -0.54
    と思われる
    -0.53
    assioned
    -0.53
    !*\
    -0.51
    Specified
    -0.50
     Customized
    -0.50
    POSITIVE LOGITS
     being
    1.51
     having
    1.48
     étant
    1.37
     needing
    1.27
    having
    1.22
    being
    1.18
     fiind
    1.12
    étant
    1.05
     sendo
    1.04
     HAVING
    1.02
    Activations Density 0.246%

    No Known Activations