© 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. 14798
    Prev
    Next
    INDEX
    Explanations

    modal verbs and phrases indicating ability or necessity

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

    preceding modal verbs

    np_acts-logits-general · gemini-2.0-flash

    ability and permission to act

    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
     ostensibly
    -0.71
    jsonwebtoken
    -0.68
    ScopeManager
    -0.67
    netta
    -0.65
     يتيمه
    -0.65
     unwit
    -0.64
    fromnode
    -0.62
    ({},
    -0.62
    ($"{
    -0.61
    AutoresizingMask
    -0.61
    POSITIVE LOGITS
     prouve
    0.65
     till
    0.59
     Hence
    0.57
     possibile
    0.53
    Hence
    0.53
    Šaltiniai
    0.53
    Till
    0.52
     acordo
    0.51
     sûrement
    0.51
    dasarkan
    0.51
    Activations Density 0.378%

    No Known Activations