© 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. 16-GEMMASCOPE-RES-16K
    11. 13395
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating ability or possibility

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

    "can" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    ability or possibility of action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.79
    GEBURTSDATUM
    -0.74
    WriteTagHelper
    -0.73
     CURIAM
    -0.66
    Personensuche
    -0.65
     nisi
    -0.63
     azzurro
    -0.60
     inoxid
    -0.60
    Життєпис
    -0.59
    UnusedPrivate
    -0.59
    POSITIVE LOGITS
     be
    1.38
     also
    1.16
     easily
    1.05
     certainly
    0.99
     still
    0.98
     have
    0.95
     always
    0.90
     actually
    0.89
     definitely
    0.87
     make
    0.87
    Activations Density 0.232%

    No Known Activations