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

    Neuronpedia

    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. 4286
    Prev
    Next
    INDEX
    Explanations

    the verb "is" and its variations, highlighting its frequent use in various contexts

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

    Precedes "is" followed by "a" or "an"

    np_acts-logits-general · gemini-2.0-flash

    is followed by a or an

    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
     فريبيس
    -1.05
    ISupport
    -0.94
     kasarigan
    -0.91
    bkz
    -0.84
    MethodManager
    -0.80
    Externé
    -0.79
     nakalista
    -0.78
    antaranya
    -0.77
     itſelf
    -0.76
     betweenstory
    -0.74
    POSITIVE LOGITS
     a
    1.34
     an
    1.21
     the
    0.95
     another
    0.90
     one
    0.73
     μια
    0.68
     een
    0.65
     our
    0.62
    an
    0.58
     eine
    0.58
    Activations Density 0.385%

    No Known Activations