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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10134
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "to be" in various forms

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

    Following "is" or "was"

    np_acts-logits-general · gemini-2.0-flash

    states or conditions after 'is'/'was'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OrNil
    -0.65
     يتيمه
    -0.57
    iolis
    -0.56
    MENAFN
    -0.55
    #+#
    -0.55
    addContainerGap
    -0.54
    RefNanny
    -0.53
    cheria
    -0.52
    izante
    -0.51
    rairie
    -0.51
    POSITIVE LOGITS
     married
    0.90
     obsessed
    0.75
     someone
    0.74
     seorang
    0.71
     unmarried
    0.69
     fluent
    0.67
     part
    0.66
     aware
    0.66
     addicted
    0.66
     versed
    0.66
    Activations Density 0.475%

    No Known Activations