© 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. 16285
    Prev
    Next
    INDEX
    Explanations

    emphasized phrases indicating importance or relevance

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

    Follows "particularly" or "especially"

    np_acts-logits-general · gemini-2.0-flash

    especially if, since, when

    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
    }();
    -0.66
     prostu
    -0.64
     EconPapers
    -0.63
    SpringBootTest
    -0.61
     FetchType
    -0.61
    ('');
    -0.60
     незавершена
    -0.57
    脚注の使い方
    -0.56
     }</
    -0.56
    })();
    -0.55
    POSITIVE LOGITS
     those
    1.03
     when
    0.93
     if
    0.82
    those
    0.79
     dacă
    0.71
     since
    0.69
     wenn
    0.69
     hvis
    0.68
     ones
    0.68
    cially
    0.67
    Activations Density 0.122%

    No Known Activations